Showing 1–50 of 88 results for author: Pal, U

Reliability-Aware Weighted Multi-Scale Spatio-Temporal Maps for Heart Rate Monitoring

Authors: Arpan Bairagi, Rakesh Dey, Siladittya Manna, Umapada Pal

Abstract: Remote photoplethysmography (rPPG) allows for the contactless estimation of physiological signals from facial videos by analyzing subtle skin color changes. However, rPPG signals are extremely susceptible to illumination changes, motion, shadows, and specular reflections, resulting in low-quality signals in unconstrained environments. To overcome these issues, we present a Reliability-Aware Weight… ▽ More Remote photoplethysmography (rPPG) allows for the contactless estimation of physiological signals from facial videos by analyzing subtle skin color changes. However, rPPG signals are extremely susceptible to illumination changes, motion, shadows, and specular reflections, resulting in low-quality signals in unconstrained environments. To overcome these issues, we present a Reliability-Aware Weighted Multi-Scale Spatio-Temporal (WMST) map that models pixel reliability through the suppression of environmental noises. These noises are modeled using different weighting strategies to focus on more physiologically valid areas. Leveraging the WMST map, we develop an SSL contrastive learning approach based on Swin-Unet, where positive pairs are generated from conventional rPPG signals and temporally expanded WMST maps. Moreover, we introduce a new High-High-High (HHH) wavelet map as a negative example that maintains motion and structural details while filtering out physiological information. Here, our aim is to estimate heart rate (HR), and the experiments on public rPPG benchmarks show that our approach enhances motion and illumination robustness with lower HR estimation error and higher Pearson correlation than existing Self-Supervised Learning (SSL) based rPPG methods. △ Less

Submitted 27 March, 2026; originally announced March 2026.

Comments: 6 pages, 4 figures. Under review at ICIP 2026

Towards Robust Cross-Dataset Object Detection Generalization under Domain Specificity

Authors: Ritabrata Chakraborty, Hrishit Mitra, Shivakumara Palaiahnakote, Umapada Pal

Abstract: Object detectors often perform well in-distribution, yet degrade sharply on a different benchmark. We study cross-dataset object detection (CD-OD) through a lens of setting specificity. We group benchmarks into setting-agnostic datasets with diverse everyday scenes and setting-specific datasets tied to a narrow environment, and evaluate a standard detector family across all train--test pairs. This… ▽ More Object detectors often perform well in-distribution, yet degrade sharply on a different benchmark. We study cross-dataset object detection (CD-OD) through a lens of setting specificity. We group benchmarks into setting-agnostic datasets with diverse everyday scenes and setting-specific datasets tied to a narrow environment, and evaluate a standard detector family across all train--test pairs. This reveals a clear structure in CD-OD: transfer within the same setting type is relatively stable, while transfer across setting types drops substantially and is often asymmetric. The most severe breakdowns occur when transferring from specific sources to agnostic targets, and persist after open-label alignment, indicating that domain shift dominates in the hardest regimes. To disentangle domain shift from label mismatch, we compare closed-label transfer with an open-label protocol that maps predicted classes to the nearest target label using CLIP similarity. Open-label evaluation yields consistent but bounded gains, and many corrected cases correspond to semantic near-misses supported by the image evidence. Overall, we provide a principled characterization of CD-OD under setting specificity and practical guidance for evaluating detectors under distribution shift. Code will be released at \href{[https://github.com/Ritabrata04/cdod-icpr.git}{https://github.com/Ritabrata04/cdod-icpr}. △ Less

Submitted 14 January, 2026; originally announced January 2026.

Comments: 15 pages, 4 figures, 6 tables

Generative AI in Depth: A Survey of Recent Advances, Model Variants, and Real-World Applications

Authors: Shamim Yazdani, Akansha Singh, Nripsuta Saxena, Zichong Wang, Avash Palikhe, Deng Pan, Umapada Pal, Jie Yang, Wenbin Zhang

Abstract: In recent years, deep learning based generative models, particularly Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Diffusion Models (DMs), have been instrumental in in generating diverse, high-quality content across various domains, such as image and video synthesis. This capability has led to widespread adoption of these models and has captured strong public interes… ▽ More In recent years, deep learning based generative models, particularly Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Diffusion Models (DMs), have been instrumental in in generating diverse, high-quality content across various domains, such as image and video synthesis. This capability has led to widespread adoption of these models and has captured strong public interest. As they continue to advance at a rapid pace, the growing volume of research, expanding application areas, and unresolved technical challenges make it increasingly difficult to stay current. To address this need, this survey introduces a comprehensive taxonomy that organizes the literature and provides a cohesive framework for understanding the development of GANs, VAEs, and DMs, including their many variants and combined approaches. We highlight key innovations that have improved the quality, diversity, and controllability of generated outputs, reflecting the expanding potential of generative artificial intelligence. In addition to summarizing technical progress, we examine rising ethical concerns, including the risks of misuse and the broader societal impact of synthetic media. Finally, we outline persistent challenges and propose future research directions, offering a structured and forward looking perspective for researchers in this fast evolving field. △ Less

Submitted 23 October, 2025; originally announced October 2025.

Comments: Accepted by the Journal of Big Data

TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering

Authors: Ayan Banerjee, Josep Lladós, Umapada Pal, Anjan Dutta

Abstract: Text-to-story visualization is challenging due to the need for consistent interaction among multiple characters across frames. Existing methods struggle with character consistency, leading to artifact generation and inaccurate dialogue rendering, which results in disjointed storytelling. In response, we introduce TaleDiffusion, a novel framework for generating multi-character stories with an itera… ▽ More Text-to-story visualization is challenging due to the need for consistent interaction among multiple characters across frames. Existing methods struggle with character consistency, leading to artifact generation and inaccurate dialogue rendering, which results in disjointed storytelling. In response, we introduce TaleDiffusion, a novel framework for generating multi-character stories with an iterative process, maintaining character consistency, and accurate dialogue assignment via postprocessing. Given a story, we use a pre-trained LLM to generate per-frame descriptions, character details, and dialogues via in-context learning, followed by a bounded attention-based per-box mask technique to control character interactions and minimize artifacts. We then apply an identity-consistent self-attention mechanism to ensure character consistency across frames and region-aware cross-attention for precise object placement. Dialogues are also rendered as bubbles and assigned to characters via CLIPSeg. Experimental results demonstrate that TaleDiffusion outperforms existing methods in consistency, noise reduction, and dialogue rendering. △ Less

Submitted 4 September, 2025; originally announced September 2025.

Privacy-enhancing Sclera Segmentation Benchmarking Competition: SSBC 2025

Authors: Matej Vitek, Darian Tomašević, Abhijit Das, Sabari Nathan, Gökhan Özbulak, Gözde Ayşe Tataroğlu Özbulak, Jean-Paul Calbimonte, André Anjos, Hariohm Hemant Bhatt, Dhruv Dhirendra Premani, Jay Chaudhari, Caiyong Wang, Jian Jiang, Chi Zhang, Qi Zhang, Iyyakutti Iyappan Ganapathi, Syed Sadaf Ali, Divya Velayudan, Maregu Assefa, Naoufel Werghi, Zachary A. Daniels, Leeon John, Ritesh Vyas, Jalil Nourmohammadi Khiarak, Taher Akbari Saeed , et al. (10 additional authors not shown)

Abstract: This paper presents a summary of the 2025 Sclera Segmentation Benchmarking Competition (SSBC), which focused on the development of privacy-preserving sclera-segmentation models trained using synthetically generated ocular images. The goal of the competition was to evaluate how well models trained on synthetic data perform in comparison to those trained on real-world datasets. The competition featu… ▽ More This paper presents a summary of the 2025 Sclera Segmentation Benchmarking Competition (SSBC), which focused on the development of privacy-preserving sclera-segmentation models trained using synthetically generated ocular images. The goal of the competition was to evaluate how well models trained on synthetic data perform in comparison to those trained on real-world datasets. The competition featured two tracks: $(i)$ one relying solely on synthetic data for model development, and $(ii)$ one combining/mixing synthetic with (a limited amount of) real-world data. A total of nine research groups submitted diverse segmentation models, employing a variety of architectural designs, including transformer-based solutions, lightweight models, and segmentation networks guided by generative frameworks. Experiments were conducted across three evaluation datasets containing both synthetic and real-world images, collected under diverse conditions. Results show that models trained entirely on synthetic data can achieve competitive performance, particularly when dedicated training strategies are employed, as evidenced by the top performing models that achieved $F_1$ scores of over $0.8$ in the synthetic data track. Moreover, performance gains in the mixed track were often driven more by methodological choices rather than by the inclusion of real data, highlighting the promise of synthetic data for privacy-aware biometric development. The code and data for the competition is available at: https://github.com/dariant/SSBC_2025. △ Less

Submitted 14 August, 2025; originally announced August 2025.

Comments: IEEE International Joint Conference on Biometrics (IJCB) 2025, 13 pages

A Transformer Based Handwriting Recognition System Jointly Using Online and Offline Features

Authors: Ayush Lodh, Ritabrata Chakraborty, Shivakumara Palaiahnakote, Umapada Pal

Abstract: We posit that handwriting recognition benefits from complementary cues carried by the rasterized complex glyph and the pen's trajectory, yet most systems exploit only one modality. We introduce an end-to-end network that performs early fusion of offline images and online stroke data within a shared latent space. A patch encoder converts the grayscale crop into fixed-length visual tokens, while a l… ▽ More We posit that handwriting recognition benefits from complementary cues carried by the rasterized complex glyph and the pen's trajectory, yet most systems exploit only one modality. We introduce an end-to-end network that performs early fusion of offline images and online stroke data within a shared latent space. A patch encoder converts the grayscale crop into fixed-length visual tokens, while a lightweight transformer embeds the $(x, y, \text{pen})$ sequence. Learnable latent queries attend jointly to both token streams, yielding context-enhanced stroke embeddings that are pooled and decoded under a cross-entropy loss objective. Because integration occurs before any high-level classification, temporal cues reinforce each other during representation learning, producing stronger writer independence. Comprehensive experiments on IAMOn-DB and VNOn-DB demonstrate that our approach achieves state-of-the-art accuracy, exceeding previous bests by up to 1\%. Our study also shows adaptation of this pipeline with gesturification on the ISI-Air dataset. Our code can be found here. △ Less

Submitted 25 June, 2025; originally announced June 2025.

Comments: 15 pages, 7 figures

Conformal uncertainty quantification to evaluate predictive fairness of foundation AI model for skin lesion classes across patient demographics

Authors: Swarnava Bhattacharyya, Umapada Pal, Tapabrata Chakraborti

Abstract: Deep learning based diagnostic AI systems based on medical images are starting to provide similar performance as human experts. However these data hungry complex systems are inherently black boxes and therefore slow to be adopted for high risk applications like healthcare. This problem of lack of transparency is exacerbated in the case of recent large foundation models, which are trained in a self… ▽ More Deep learning based diagnostic AI systems based on medical images are starting to provide similar performance as human experts. However these data hungry complex systems are inherently black boxes and therefore slow to be adopted for high risk applications like healthcare. This problem of lack of transparency is exacerbated in the case of recent large foundation models, which are trained in a self supervised manner on millions of data points to provide robust generalisation across a range of downstream tasks, but the embeddings generated from them happen through a process that is not interpretable, and hence not easily trustable for clinical applications. To address this timely issue, we deploy conformal analysis to quantify the predictive uncertainty of a vision transformer (ViT) based foundation model across patient demographics with respect to sex, age and ethnicity for the tasks of skin lesion classification using several public benchmark datasets. The significant advantage of this method is that conformal analysis is method independent and it not only provides a coverage guarantee at population level but also provides an uncertainty score for each individual. We used a model-agnostic dynamic F1-score-based sampling during model training, which helped to stabilize the class imbalance and we investigate the effects on uncertainty quantification (UQ) with or without this bias mitigation step. Thus we show how this can be used as a fairness metric to evaluate the robustness of the feature embeddings of the foundation model (Google DermFoundation) and thus advance the trustworthiness and fairness of clinical AI. △ Less

Submitted 31 March, 2025; originally announced March 2025.

A Context-Driven Training-Free Network for Lightweight Scene Text Segmentation and Recognition

Authors: Ritabrata Chakraborty, Shivakumara Palaiahnakote, Umapada Pal, Cheng-Lin Liu

Abstract: Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively expensive for real-time scenarios. In such cases, the deployment of heavy models becomes impractical due to constraints on memory, computational resources, and latency. To address these challenges, we propose a novel, training-free plug-and-play framework that… ▽ More Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively expensive for real-time scenarios. In such cases, the deployment of heavy models becomes impractical due to constraints on memory, computational resources, and latency. To address these challenges, we propose a novel, training-free plug-and-play framework that leverages the strengths of pre-trained text recognizers while minimizing redundant computations. Our approach uses context-based understanding and introduces an attention-based segmentation stage, which refines candidate text regions at the pixel level, improving downstream recognition. Instead of performing traditional text detection that follows a block-level comparison between feature map and source image and harnesses contextual information using pretrained captioners, allowing the framework to generate word predictions directly from scene context.Candidate texts are semantically and lexically evaluated to get a final score. Predictions that meet or exceed a pre-defined confidence threshold bypass the heavier process of end-to-end text STR profiling, ensuring faster inference and cutting down on unnecessary computations. Experiments on public benchmarks demonstrate that our paradigm achieves performance on par with state-of-the-art systems, yet requires substantially fewer resources. △ Less

Submitted 19 March, 2025; originally announced March 2025.

d-Sketch: Improving Visual Fidelity of Sketch-to-Image Translation with Pretrained Latent Diffusion Models without Retraining

Authors: Prasun Roy, Saumik Bhattacharya, Subhankar Ghosh, Umapada Pal, Michael Blumenstein

Abstract: Structural guidance in an image-to-image translation allows intricate control over the shapes of synthesized images. Generating high-quality realistic images from user-specified rough hand-drawn sketches is one such task that aims to impose a structural constraint on the conditional generation process. While the premise is intriguing for numerous use cases of content creation and academic research… ▽ More Structural guidance in an image-to-image translation allows intricate control over the shapes of synthesized images. Generating high-quality realistic images from user-specified rough hand-drawn sketches is one such task that aims to impose a structural constraint on the conditional generation process. While the premise is intriguing for numerous use cases of content creation and academic research, the problem becomes fundamentally challenging due to substantial ambiguities in freehand sketches. Furthermore, balancing the trade-off between shape consistency and realistic generation contributes to additional complexity in the process. Existing approaches based on Generative Adversarial Networks (GANs) generally utilize conditional GANs or GAN inversions, often requiring application-specific data and optimization objectives. The recent introduction of Denoising Diffusion Probabilistic Models (DDPMs) achieves a generational leap for low-level visual attributes in general image synthesis. However, directly retraining a large-scale diffusion model on a domain-specific subtask is often extremely difficult due to demanding computation costs and insufficient data. In this paper, we introduce a technique for sketch-to-image translation by exploiting the feature generalization capabilities of a large-scale diffusion model without retraining. In particular, we use a learnable lightweight mapping network to achieve latent feature translation from source to target domain. Experimental results demonstrate that the proposed method outperforms the existing techniques in qualitative and quantitative benchmarks, allowing high-resolution realistic image synthesis from rough hand-drawn sketches. △ Less

Submitted 19 February, 2025; originally announced February 2025.

Comments: Accepted in The International Conference on Pattern Recognition (ICPR) 2024

Exploring Mutual Cross-Modal Attention for Context-Aware Human Affordance Generation

Authors: Prasun Roy, Saumik Bhattacharya, Subhankar Ghosh, Umapada Pal, Michael Blumenstein

Abstract: Human affordance learning investigates contextually relevant novel pose prediction such that the estimated pose represents a valid human action within the scene. While the task is fundamental to machine perception and automated interactive navigation agents, the exponentially large number of probable pose and action variations make the problem challenging and non-trivial. However, the existing dat… ▽ More Human affordance learning investigates contextually relevant novel pose prediction such that the estimated pose represents a valid human action within the scene. While the task is fundamental to machine perception and automated interactive navigation agents, the exponentially large number of probable pose and action variations make the problem challenging and non-trivial. However, the existing datasets and methods for human affordance prediction in 2D scenes are significantly limited in the literature. In this paper, we propose a novel cross-attention mechanism to encode the scene context for affordance prediction by mutually attending spatial feature maps from two different modalities. The proposed method is disentangled among individual subtasks to efficiently reduce the problem complexity. First, we sample a probable location for a person within the scene using a variational autoencoder (VAE) conditioned on the global scene context encoding. Next, we predict a potential pose template from a set of existing human pose candidates using a classifier on the local context encoding around the predicted location. In the subsequent steps, we use two VAEs to sample the scale and deformation parameters for the predicted pose template by conditioning on the local context and template class. Our experiments show significant improvements over the previous baseline of human affordance injection into complex 2D scenes. △ Less

Submitted 19 February, 2025; originally announced February 2025.

Comments: 11 pages

CoCoNO: Attention Contrast-and-Complete for Initial Noise Optimization in Text-to-Image Synthesis

Authors: Aravindan Sundaram, Ujjayan Pal, Abhimanyu Chauhan, Aishwarya Agarwal, Srikrishna Karanam

Abstract: Despite recent advancements in text-to-image models, achieving semantically accurate images in text-to-image diffusion models is a persistent challenge. While existing initial latent optimization methods have demonstrated impressive performance, we identify two key limitations: (a) attention neglect, where the synthesized image omits certain subjects from the input prompt because they do not have… ▽ More Despite recent advancements in text-to-image models, achieving semantically accurate images in text-to-image diffusion models is a persistent challenge. While existing initial latent optimization methods have demonstrated impressive performance, we identify two key limitations: (a) attention neglect, where the synthesized image omits certain subjects from the input prompt because they do not have a designated segment in the self-attention map despite despite having a high-response cross-attention, and (b) attention interference, where the generated image has mixed-up properties of multiple subjects because of a conflicting overlap between cross- and self-attention maps of different subjects. To address these limitations, we introduce CoCoNO, a new algorithm that optimizes the initial latent by leveraging the complementary information within self-attention and cross-attention maps. Our method introduces two new loss functions: the attention contrast loss, which minimizes undesirable overlap by ensuring each self-attention segment is exclusively linked to a specific subject's cross attention map, and the attention complete loss, which maximizes the activation within these segments to guarantee that each subject is fully and distinctly represented. Our approach operates within a noise optimization framework, avoiding the need to retrain base models. Through extensive experiments on multiple benchmarks, we demonstrate that CoCoNO significantly improves text-image alignment and outperforms the current state of the art. △ Less

Submitted 25 November, 2024; originally announced November 2024.

Comments: 15 pages, 12 figures

Decorrelation-based Self-Supervised Visual Representation Learning for Writer Identification

Authors: Arkadip Maitra, Shree Mitra, Siladittya Manna, Saumik Bhattacharya, Umapada Pal

Abstract: Self-supervised learning has developed rapidly over the last decade and has been applied in many areas of computer vision. Decorrelation-based self-supervised pretraining has shown great promise among non-contrastive algorithms, yielding performance at par with supervised and contrastive self-supervised baselines. In this work, we explore the decorrelation-based paradigm of self-supervised learnin… ▽ More Self-supervised learning has developed rapidly over the last decade and has been applied in many areas of computer vision. Decorrelation-based self-supervised pretraining has shown great promise among non-contrastive algorithms, yielding performance at par with supervised and contrastive self-supervised baselines. In this work, we explore the decorrelation-based paradigm of self-supervised learning and apply the same to learning disentangled stroke features for writer identification. Here we propose a modified formulation of the decorrelation-based framework named SWIS which was proposed for signature verification by standardizing the features along each dimension on top of the existing framework. We show that the proposed framework outperforms the contemporary self-supervised learning framework on the writer identification benchmark and also outperforms several supervised methods as well. To the best of our knowledge, this work is the first of its kind to apply self-supervised learning for learning representations for writer verification tasks. △ Less

Submitted 2 October, 2024; originally announced October 2024.

SafeTail: Efficient Tail Latency Optimization in Edge Service Scheduling via Computational Redundancy Management

Authors: Jyoti Shokhanda, Utkarsh Pal, Aman Kumar, Soumi Chattopadhyay, Arani Bhattacharya

Abstract: Optimizing tail latency while efficiently managing computational resources is crucial for delivering high-performance, latency-sensitive services in edge computing. Emerging applications, such as augmented reality, require low-latency computing services with high reliability on user devices, which often have limited computational capabilities. Consequently, these devices depend on nearby edge serv… ▽ More Optimizing tail latency while efficiently managing computational resources is crucial for delivering high-performance, latency-sensitive services in edge computing. Emerging applications, such as augmented reality, require low-latency computing services with high reliability on user devices, which often have limited computational capabilities. Consequently, these devices depend on nearby edge servers for processing. However, inherent uncertainties in network and computation latencies stemming from variability in wireless networks and fluctuating server loads make service delivery on time challenging. Existing approaches often focus on optimizing median latency but fall short of addressing the specific challenges of tail latency in edge environments, particularly under uncertain network and computational conditions. Although some methods do address tail latency, they typically rely on fixed or excessive redundancy and lack adaptability to dynamic network conditions, often being designed for cloud environments rather than the unique demands of edge computing. In this paper, we introduce SafeTail, a framework that meets both median and tail response time targets, with tail latency defined as latency beyond the 90^th percentile threshold. SafeTail addresses this challenge by selectively replicating services across multiple edge servers to meet target latencies. SafeTail employs a reward-based deep learning framework to learn optimal placement strategies, balancing the need to achieve target latencies with minimizing additional resource usage. Through trace-driven simulations, SafeTail demonstrated near-optimal performance and outperformed most baseline strategies across three diverse services. △ Less

Submitted 30 August, 2024; originally announced August 2024.

Comments: This work has been submitted to the IEEE for possible publication

FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting

Authors: Alloy Das, Sanket Biswas, Umapada Pal, Josep Lladós, Saumik Bhattacharya

Abstract: The proliferation of scene text in both structured and unstructured environments presents significant challenges in optical character recognition (OCR), necessitating more efficient and robust text spotting solutions. This paper presents FastTextSpotter, a framework that integrates a Swin Transformer visual backbone with a Transformer Encoder-Decoder architecture, enhanced by a novel, faster self-… ▽ More The proliferation of scene text in both structured and unstructured environments presents significant challenges in optical character recognition (OCR), necessitating more efficient and robust text spotting solutions. This paper presents FastTextSpotter, a framework that integrates a Swin Transformer visual backbone with a Transformer Encoder-Decoder architecture, enhanced by a novel, faster self-attention unit, SAC2, to improve processing speeds while maintaining accuracy. FastTextSpotter has been validated across multiple datasets, including ICDAR2015 for regular texts and CTW1500 and TotalText for arbitrary-shaped texts, benchmarking against current state-of-the-art models. Our results indicate that FastTextSpotter not only achieves superior accuracy in detecting and recognizing multilingual scene text (English and Vietnamese) but also improves model efficiency, thereby setting new benchmarks in the field. This study underscores the potential of advanced transformer architectures in improving the adaptability and speed of text spotting applications in diverse real-world settings. The dataset, code, and pre-trained models have been released in our Github. △ Less

Submitted 12 March, 2025; v1 submitted 27 August, 2024; originally announced August 2024.

Comments: Accepted in ICPR 2024

Correlation Weighted Prototype-based Self-Supervised One-Shot Segmentation of Medical Images

Authors: Siladittya Manna, Saumik Bhattacharya, Umapada Pal

Abstract: Medical image segmentation is one of the domains where sufficient annotated data is not available. This necessitates the application of low-data frameworks like few-shot learning. Contemporary prototype-based frameworks often do not account for the variation in features within the support and query images, giving rise to a large variance in prototype alignment. In this work, we adopt a prototype-b… ▽ More Medical image segmentation is one of the domains where sufficient annotated data is not available. This necessitates the application of low-data frameworks like few-shot learning. Contemporary prototype-based frameworks often do not account for the variation in features within the support and query images, giving rise to a large variance in prototype alignment. In this work, we adopt a prototype-based self-supervised one-way one-shot learning framework using pseudo-labels generated from superpixels to learn the semantic segmentation task itself. We use a correlation-based probability score to generate a dynamic prototype for each query pixel from the bag of prototypes obtained from the support feature map. This weighting scheme helps to give a higher weightage to contextually related prototypes. We also propose a quadrant masking strategy in the downstream segmentation task by utilizing prior domain information to discard unwanted false positives. We present extensive experimentations and evaluations on abdominal CT and MR datasets to show that the proposed simple but potent framework performs at par with the state-of-the-art methods. △ Less

Submitted 12 August, 2024; originally announced August 2024.

Comments: Accepted to ICPR 2024

Assessing the Variety of a Concept Space Using an Unbiased Estimate of Rao's Quadratic Index

Authors: Anubhab Majumder, Ujjwal Pal, Amaresh Chakrabarti

Abstract: Past research relates design creativity to 'divergent thinking,' i.e., how well the concept space is explored during the early phase of design. Researchers have argued that generating several concepts would increase the chances of producing better design solutions. 'Variety' is one of the parameters by which one can quantify the breadth of a concept space explored by the designers. It is useful to… ▽ More Past research relates design creativity to 'divergent thinking,' i.e., how well the concept space is explored during the early phase of design. Researchers have argued that generating several concepts would increase the chances of producing better design solutions. 'Variety' is one of the parameters by which one can quantify the breadth of a concept space explored by the designers. It is useful to assess variety at the conceptual design stage because, at this stage, designers have the freedom to explore different solution principles so as to satisfy a design problem with substantially novel concepts. This article elaborates on and critically examines the existing variety metrics from the engineering design literature, discussing their limitations. A new distance-based variety metric is proposed, along with a prescriptive framework to support the assessment process. This framework uses the SAPPhIRE model of causality as a knowledge representation scheme to measure the real-valued distance between two design concepts. The proposed framework is implemented in a software tool called 'VariAnT.' Furthermore, the tool's application is demonstrated through an illustrative example. △ Less

Submitted 1 August, 2024; originally announced August 2024.

MDIW-13: a New Multi-Lingual and Multi-Script Database and Benchmark for Script Identification

Authors: Miguel A. Ferrer, Abhijit Das, Moises Diaz, Aythami Morales, Cristina Carmona-Duarte, Umapada Pal

Abstract: Script identification plays a vital role in applications that involve handwriting and document analysis within a multi-script and multi-lingual environment. Moreover, it exhibits a profound connection with human cognition. This paper provides a new database for benchmarking script identification algorithms, which contains both printed and handwritten documents collected from a wide variety of scri… ▽ More Script identification plays a vital role in applications that involve handwriting and document analysis within a multi-script and multi-lingual environment. Moreover, it exhibits a profound connection with human cognition. This paper provides a new database for benchmarking script identification algorithms, which contains both printed and handwritten documents collected from a wide variety of scripts, such as Arabic, Bengali (Bangla), Gujarati, Gurmukhi, Devanagari, Japanese, Kannada, Malayalam, Oriya, Roman, Tamil, Telugu, and Thai. The dataset consists of 1,135 documents scanned from local newspaper and handwritten letters as well as notes from different native writers. Further, these documents are segmented into lines and words, comprising a total of 13,979 and 86,655 lines and words, respectively, in the dataset. Easy-to-go benchmarks are proposed with handcrafted and deep learning methods. The benchmark includes results at the document, line, and word levels with printed and handwritten documents. Results of script identification independent of the document/line/word level and independent of the printed/handwritten letters are also given. The new multi-lingual database is expected to create new script identifiers, present various challenges, including identifying handwritten and printed samples and serve as a foundation for future research in script identification based on the reported results of the three benchmarks. △ Less

Submitted 29 May, 2024; originally announced May 2024.

Journal ref: Cognitive Computation, Volume 16, pages 131 to 157,(2024)

CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusion

Authors: Ayan Banerjee, Nityanand Mathur, Josep Llados, Umapada Pal, Anjan Dutta

Abstract: Generating VectorArt from text prompts is a challenging vision task, requiring diverse yet realistic depictions of the seen as well as unseen entities. However, existing research has been mostly limited to the generation of single objects, rather than comprehensive scenes comprising multiple elements. In response, this work introduces SVGCraft, a novel end-to-end framework for the creation of vect… ▽ More Generating VectorArt from text prompts is a challenging vision task, requiring diverse yet realistic depictions of the seen as well as unseen entities. However, existing research has been mostly limited to the generation of single objects, rather than comprehensive scenes comprising multiple elements. In response, this work introduces SVGCraft, a novel end-to-end framework for the creation of vector graphics depicting entire scenes from textual descriptions. Utilizing a pre-trained LLM for layout generation from text prompts, this framework introduces a technique for producing masked latents in specified bounding boxes for accurate object placement. It introduces a fusion mechanism for integrating attention maps and employs a diffusion U-Net for coherent composition, speeding up the drawing process. The resulting SVG is optimized using a pre-trained encoder and LPIPS loss with opacity modulation to maximize similarity. Additionally, this work explores the potential of primitive shapes in facilitating canvas completion in constrained environments. Through both qualitative and quantitative assessments, SVGCraft is demonstrated to surpass prior works in abstraction, recognizability, and detail, as evidenced by its performance metrics (CLIP-T: 0.4563, Cosine Similarity: 0.6342, Confusion: 0.66, Aesthetic: 6.7832). The code will be available at https://github.com/ayanban011/SVGCraft. △ Less

Submitted 28 November, 2025; v1 submitted 30 March, 2024; originally announced April 2024.

GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation

Authors: Ayan Banerjee, Sanket Biswas, Josep Lladós, Umapada Pal

Abstract: Object detection in documents is a key step to automate the structural elements identification process in a digital or scanned document through understanding the hierarchical structure and relationships between different elements. Large and complex models, while achieving high accuracy, can be computationally expensive and memory-intensive, making them impractical for deployment on resource constr… ▽ More Object detection in documents is a key step to automate the structural elements identification process in a digital or scanned document through understanding the hierarchical structure and relationships between different elements. Large and complex models, while achieving high accuracy, can be computationally expensive and memory-intensive, making them impractical for deployment on resource constrained devices. Knowledge distillation allows us to create small and more efficient models that retain much of the performance of their larger counterparts. Here we present a graph-based knowledge distillation framework to correctly identify and localize the document objects in a document image. Here, we design a structured graph with nodes containing proposal-level features and edges representing the relationship between the different proposal regions. Also, to reduce text bias an adaptive node sampling strategy is designed to prune the weight distribution and put more weightage on non-text nodes. We encode the complete graph as a knowledge representation and transfer it from the teacher to the student through the proposed distillation loss by effectively capturing both local and global information concurrently. Extensive experimentation on competitive benchmarks demonstrates that the proposed framework outperforms the current state-of-the-art approaches. The code will be available at: https://github.com/ayanban011/GraphKD. △ Less

Submitted 20 February, 2024; v1 submitted 17 February, 2024; originally announced February 2024.

Static and Dynamic Synthesis of Bengali and Devanagari Signatures

Authors: Miguel A. Ferrer, Sukalpa Chanda, Moises Diaz, Chayan Kr. Banerjee, Anirban Majumdar, Cristina Carmona-Duarte, Parikshit Acharya, Umapada Pal

Abstract: Developing an automatic signature verification system is challenging and demands a large number of training samples. This is why synthetic handwriting generation is an emerging topic in document image analysis. Some handwriting synthesizers use the motor equivalence model, the well-established hypothesis from neuroscience, which analyses how a human being accomplishes movement. Specifically, a mot… ▽ More Developing an automatic signature verification system is challenging and demands a large number of training samples. This is why synthetic handwriting generation is an emerging topic in document image analysis. Some handwriting synthesizers use the motor equivalence model, the well-established hypothesis from neuroscience, which analyses how a human being accomplishes movement. Specifically, a motor equivalence model divides human actions into two steps: 1) the effector independent step at cognitive level and 2) the effector dependent step at motor level. In fact, recent work reports the successful application to Western scripts of a handwriting synthesizer, based on this theory. This paper aims to adapt this scheme for the generation of synthetic signatures in two Indic scripts, Bengali (Bangla), and Devanagari (Hindi). For this purpose, we use two different online and offline databases for both Bengali and Devanagari signatures. This paper reports an effective synthesizer for static and dynamic signatures written in Devanagari or Bengali scripts. We obtain promising results with artificially generated signatures in terms of appearance and performance when we compare the results with those for real signatures. △ Less

Submitted 30 January, 2024; originally announced January 2024.

Comments: Accepted version. Published on IEEE Transactions on Cybernetics [ISSN 2168-2267], v. 48(10), p. 2896-2907

Journal ref: IEEE Transactions on Cybernetics, v. 48(10), p. 2896-2907, 2018

A Layer-Wise Tokens-to-Token Transformer Network for Improved Historical Document Image Enhancement

Authors: Risab Biswas, Swalpa Kumar Roy, Umapada Pal

Abstract: Document image enhancement is a fundamental and important stage for attaining the best performance in any document analysis assignment because there are many degradation situations that could harm document images, making it more difficult to recognize and analyze them. In this paper, we propose \textbf{T2T-BinFormer} which is a novel document binarization encoder-decoder architecture based on a To… ▽ More Document image enhancement is a fundamental and important stage for attaining the best performance in any document analysis assignment because there are many degradation situations that could harm document images, making it more difficult to recognize and analyze them. In this paper, we propose \textbf{T2T-BinFormer} which is a novel document binarization encoder-decoder architecture based on a Tokens-to-token vision transformer. Each image is divided into a set of tokens with a defined length using the ViT model, which is then applied several times to model the global relationship between the tokens. However, the conventional tokenization of input data does not adequately reflect the crucial local structure between adjacent pixels of the input image, which results in low efficiency. Instead of using a simple ViT and hard splitting of images for the document image enhancement task, we employed a progressive tokenization technique to capture this local information from an image to achieve more effective results. Experiments on various DIBCO and H-DIBCO benchmarks demonstrate that the proposed model outperforms the existing CNN and ViT-based state-of-the-art methods. In this research, the primary area of examination is the application of the proposed architecture to the task of document binarization. The source code will be made available at https://github.com/RisabBiswas/T2T-BinFormer. △ Less

Submitted 6 December, 2023; originally announced December 2023.

Comments: arXiv admin note: text overlap with arXiv:2312.03568

DocBinFormer: A Two-Level Transformer Network for Effective Document Image Binarization

Authors: Risab Biswas, Swalpa Kumar Roy, Ning Wang, Umapada Pal, Guang-Bin Huang

Abstract: In real life, various degradation scenarios exist that might damage document images, making it harder to recognize and analyze them, thus binarization is a fundamental and crucial step for achieving the most optimal performance in any document analysis task. We propose DocBinFormer (Document Binarization Transformer), a novel two-level vision transformer (TL-ViT) architecture based on vision trans… ▽ More In real life, various degradation scenarios exist that might damage document images, making it harder to recognize and analyze them, thus binarization is a fundamental and crucial step for achieving the most optimal performance in any document analysis task. We propose DocBinFormer (Document Binarization Transformer), a novel two-level vision transformer (TL-ViT) architecture based on vision transformers for effective document image binarization. The presented architecture employs a two-level transformer encoder to effectively capture both global and local feature representation from the input images. These complimentary bi-level features are exploited for efficient document image binarization, resulting in improved results for system-generated as well as handwritten document images in a comprehensive approach. With the absence of convolutional layers, the transformer encoder uses the pixel patches and sub-patches along with their positional information to operate directly on them, while the decoder generates a clean (binarized) output image from the latent representation of the patches. Instead of using a simple vision transformer block to extract information from the image patches, the proposed architecture uses two transformer blocks for greater coverage of the extracted feature space on a global and local scale. The encoded feature representation is used by the decoder block to generate the corresponding binarized output. Extensive experiments on a variety of DIBCO and H-DIBCO benchmarks show that the proposed model outperforms state-of-the-art techniques on four metrics. The source code will be made available at https://github.com/RisabBiswas/DocBinFormer. △ Less

Submitted 6 December, 2023; originally announced December 2023.

Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance

Authors: Alloy Das, Sanket Biswas, Ayan Banerjee, Josep Lladós, Umapada Pal, Saumik Bhattacharya

Abstract: The adaptation capability to a wide range of domains is crucial for scene text spotting models when deployed to real-world conditions. However, existing state-of-the-art (SOTA) approaches usually incorporate scene text detection and recognition simply by pretraining on natural scene text datasets, which do not directly exploit the intermediate feature representations between multiple domains. Here… ▽ More The adaptation capability to a wide range of domains is crucial for scene text spotting models when deployed to real-world conditions. However, existing state-of-the-art (SOTA) approaches usually incorporate scene text detection and recognition simply by pretraining on natural scene text datasets, which do not directly exploit the intermediate feature representations between multiple domains. Here, we investigate the problem of domain-adaptive scene text spotting, i.e., training a model on multi-domain source data such that it can directly adapt to target domains rather than being specialized for a specific domain or scenario. Further, we investigate a transformer baseline called Swin-TESTR to focus on solving scene-text spotting for both regular and arbitrary-shaped scene text along with an exhaustive evaluation. The results clearly demonstrate the potential of intermediate representations to achieve significant performance on text spotting benchmarks across multiple domains (e.g. language, synth-to-real, and documents). both in terms of accuracy and efficiency. △ Less

Submitted 1 November, 2023; v1 submitted 2 October, 2023; originally announced October 2023.

Comments: Accepted to the 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2024)

Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenes

Authors: Alloy Das, Sanket Biswas, Umapada Pal, Josep Lladós

Abstract: When used in a real-world noisy environment, the capacity to generalize to multiple domains is essential for any autonomous scene text spotting system. However, existing state-of-the-art methods employ pretraining and fine-tuning strategies on natural scene datasets, which do not exploit the feature interaction across other complex domains. In this work, we explore and investigate the problem of d… ▽ More When used in a real-world noisy environment, the capacity to generalize to multiple domains is essential for any autonomous scene text spotting system. However, existing state-of-the-art methods employ pretraining and fine-tuning strategies on natural scene datasets, which do not exploit the feature interaction across other complex domains. In this work, we explore and investigate the problem of domain-agnostic scene text spotting, i.e., training a model on multi-domain source data such that it can directly generalize to target domains rather than being specialized for a specific domain or scenario. In this regard, we present the community a text spotting validation benchmark called Under-Water Text (UWT) for noisy underwater scenes to establish an important case study. Moreover, we also design an efficient super-resolution based end-to-end transformer baseline called DA-TextSpotter which achieves comparable or superior performance over existing text spotting architectures for both regular and arbitrary-shaped scene text spotting benchmarks in terms of both accuracy and model efficiency. The dataset, code and pre-trained models will be released upon acceptance. △ Less

Submitted 17 February, 2024; v1 submitted 30 September, 2023; originally announced October 2023.

Comments: Accepted to ICRA 2024

FASTER: A Font-Agnostic Scene Text Editing and Rendering Framework

Authors: Alloy Das, Sanket Biswas, Prasun Roy, Subhankar Ghosh, Umapada Pal, Michael Blumenstein, Josep Lladós, Saumik Bhattacharya

Abstract: Scene Text Editing (STE) is a challenging research problem, that primarily aims towards modifying existing texts in an image while preserving the background and the font style of the original text. Despite its utility in numerous real-world applications, existing style-transfer-based approaches have shown sub-par editing performance due to (1) complex image backgrounds, (2) diverse font attributes… ▽ More Scene Text Editing (STE) is a challenging research problem, that primarily aims towards modifying existing texts in an image while preserving the background and the font style of the original text. Despite its utility in numerous real-world applications, existing style-transfer-based approaches have shown sub-par editing performance due to (1) complex image backgrounds, (2) diverse font attributes, and (3) varying word lengths within the text. To address such limitations, in this paper, we propose a novel font-agnostic scene text editing and rendering framework, named FASTER, for simultaneously generating text in arbitrary styles and locations while preserving a natural and realistic appearance and structure. A combined fusion of target mask generation and style transfer units, with a cascaded self-attention mechanism has been proposed to focus on multi-level text region edits to handle varying word lengths. Extensive evaluation on a real-world database with further subjective human evaluation study indicates the superiority of FASTER in both scene text editing and rendering tasks, in terms of model performance and efficiency. Our code will be released upon acceptance. △ Less

Submitted 5 November, 2024; v1 submitted 5 August, 2023; originally announced August 2023.

Comments: Accepted in WACV 2025

Dynamically Scaled Temperature in Self-Supervised Contrastive Learning

Authors: Siladittya Manna, Soumitri Chattopadhyay, Rakesh Dey, Saumik Bhattacharya, Umapada Pal

Abstract: In contemporary self-supervised contrastive algorithms like SimCLR, MoCo, etc., the task of balancing attraction between two semantically similar samples and repulsion between two samples of different classes is primarily affected by the presence of hard negative samples. While the InfoNCE loss has been shown to impose penalties based on hardness, the temperature hyper-parameter is the key to regu… ▽ More In contemporary self-supervised contrastive algorithms like SimCLR, MoCo, etc., the task of balancing attraction between two semantically similar samples and repulsion between two samples of different classes is primarily affected by the presence of hard negative samples. While the InfoNCE loss has been shown to impose penalties based on hardness, the temperature hyper-parameter is the key to regulating the penalties and the trade-off between uniformity and tolerance. In this work, we focus our attention on improving the performance of InfoNCE loss in self-supervised learning by proposing a novel cosine similarity dependent temperature scaling function to effectively optimize the distribution of the samples in the feature space. We also provide mathematical analyses to support the construction of such a dynamically scaled temperature function. Experimental evidence shows that the proposed framework outperforms the contrastive loss-based SSL algorithms. △ Less

Submitted 10 May, 2024; v1 submitted 2 August, 2023; originally announced August 2023.

SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation

Authors: Ayan Banerjee, Sanket Biswas, Josep Lladós, Umapada Pal

Abstract: Instance-level segmentation of documents consists in assigning a class-aware and instance-aware label to each pixel of the image. It is a key step in document parsing for their understanding. In this paper, we present a unified transformer encoder-decoder architecture for en-to-end instance segmentation of complex layouts in document images. The method adapts a contrastive training with a mixed qu… ▽ More Instance-level segmentation of documents consists in assigning a class-aware and instance-aware label to each pixel of the image. It is a key step in document parsing for their understanding. In this paper, we present a unified transformer encoder-decoder architecture for en-to-end instance segmentation of complex layouts in document images. The method adapts a contrastive training with a mixed query selection for anchor initialization in the decoder. Later on, it performs a dot product between the obtained query embeddings and the pixel embedding map (coming from the encoder) for semantic reasoning. Extensive experimentation on competitive benchmarks like PubLayNet, PRIMA, Historical Japanese (HJ), and TableBank demonstrate that our model with SwinL backbone achieves better segmentation performance than the existing state-of-the-art approaches with the average precision of \textbf{93.72}, \textbf{54.39}, \textbf{84.65} and \textbf{98.04} respectively under one billion parameters. The code is made publicly available at: \href{https://github.com/ayanban011/SwinDocSegmenter}{github.com/ayanban011/SwinDocSegmenter} △ Less

Submitted 8 May, 2023; originally announced May 2023.

Comments: Accepted to ICDAR 2023 (San Jose, California)

Scene Text Recognition with Image-Text Matching-guided Dictionary

Authors: Jiajun Wei, Hongjian Zhan, Xiao Tu, Yue Lu, Umapada Pal

Abstract: Employing a dictionary can efficiently rectify the deviation between the visual prediction and the ground truth in scene text recognition methods. However, the independence of the dictionary on the visual features may lead to incorrect rectification of accurate visual predictions. In this paper, we propose a new dictionary language model leveraging the Scene Image-Text Matching(SITM) network, whic… ▽ More Employing a dictionary can efficiently rectify the deviation between the visual prediction and the ground truth in scene text recognition methods. However, the independence of the dictionary on the visual features may lead to incorrect rectification of accurate visual predictions. In this paper, we propose a new dictionary language model leveraging the Scene Image-Text Matching(SITM) network, which avoids the drawbacks of the explicit dictionary language model: 1) the independence of the visual features; 2) noisy choice in candidates etc. The SITM network accomplishes this by using Image-Text Contrastive (ITC) Learning to match an image with its corresponding text among candidates in the inference stage. ITC is widely used in vision-language learning to pull the positive image-text pair closer in feature space. Inspired by ITC, the SITM network combines the visual features and the text features of all candidates to identify the candidate with the minimum distance in the feature space. Our lexicon method achieves better results(93.8\% accuracy) than the ordinary method results(92.1\% accuracy) on six mainstream benchmarks. Additionally, we integrate our method with ABINet and establish new state-of-the-art results on several benchmarks. △ Less

Submitted 8 May, 2023; originally announced May 2023.

Comments: Accepted at ICDAR2023

SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation

Authors: Subhajit Maity, Sanket Biswas, Siladittya Manna, Ayan Banerjee, Josep Lladós, Saumik Bhattacharya, Umapada Pal

Abstract: Document layout analysis is a known problem to the documents research community and has been vastly explored yielding a multitude of solutions ranging from text mining, and recognition to graph-based representation, visual feature extraction, etc. However, most of the existing works have ignored the crucial fact regarding the scarcity of labeled data. With growing internet connectivity to personal… ▽ More Document layout analysis is a known problem to the documents research community and has been vastly explored yielding a multitude of solutions ranging from text mining, and recognition to graph-based representation, visual feature extraction, etc. However, most of the existing works have ignored the crucial fact regarding the scarcity of labeled data. With growing internet connectivity to personal life, an enormous amount of documents had been available in the public domain and thus making data annotation a tedious task. We address this challenge using self-supervision and unlike, the few existing self-supervised document segmentation approaches which use text mining and textual labels, we use a complete vision-based approach in pre-training without any ground-truth label or its derivative. Instead, we generate pseudo-layouts from the document images to pre-train an image encoder to learn the document object representation and localization in a self-supervised framework before fine-tuning it with an object detection model. We show that our pipeline sets a new benchmark in this context and performs at par with the existing methods and the supervised counterparts, if not outperforms. The code is made publicly available at: https://github.com/MaitySubhajit/SelfDocSeg △ Less

Submitted 20 August, 2023; v1 submitted 1 May, 2023; originally announced May 2023.

Comments: Accepted at The 17th International Conference on Document Analysis and Recognition (ICDAR 2023)

Journal ref: ICDAR 2023 (International Conference on Document Analysis and Recognition) Lecture Notes in Computer Science, vol 14187, pp. 342-360. Springer Nature

MMC: Multi-Modal Colorization of Images using Textual Descriptions

Authors: Subhankar Ghosh, Saumik Bhattacharya, Prasun Roy, Umapada Pal, Michael Blumenstein

Abstract: Handling various objects with different colors is a significant challenge for image colorization techniques. Thus, for complex real-world scenes, the existing image colorization algorithms often fail to maintain color consistency. In this work, we attempt to integrate textual descriptions as an auxiliary condition, along with the grayscale image that is to be colorized, to improve the fidelity of… ▽ More Handling various objects with different colors is a significant challenge for image colorization techniques. Thus, for complex real-world scenes, the existing image colorization algorithms often fail to maintain color consistency. In this work, we attempt to integrate textual descriptions as an auxiliary condition, along with the grayscale image that is to be colorized, to improve the fidelity of the colorization process. To do so, we have proposed a deep network that takes two inputs (grayscale image and the respective encoded text description) and tries to predict the relevant color components. Also, we have predicted each object in the image and have colorized them with their individual description to incorporate their specific attributes in the colorization process. After that, a fusion model fuses all the image objects (segments) to generate the final colorized image. As the respective textual descriptions contain color information of the objects present in the image, text encoding helps to improve the overall quality of predicted colors. In terms of performance, the proposed method outperforms existing colorization techniques in terms of LPIPS, PSNR and SSIM metrics. △ Less

Submitted 25 April, 2023; v1 submitted 24 April, 2023; originally announced April 2023.

Comments: 9 pages

ICDAR 2023 Video Text Reading Competition for Dense and Small Text

Authors: Weijia Wu, Yuzhong Zhao, Zhuang Li, Jiahong Li, Mike Zheng Shou, Umapada Pal, Dimosthenis Karatzas, Xiang Bai

Abstract: Recently, video text detection, tracking, and recognition in natural scenes are becoming very popular in the computer vision community. However, most existing algorithms and benchmarks focus on common text cases (e.g., normal size, density) and single scenarios, while ignoring extreme video text challenges, i.e., dense and small text in various scenarios. In this competition report, we establish a… ▽ More Recently, video text detection, tracking, and recognition in natural scenes are becoming very popular in the computer vision community. However, most existing algorithms and benchmarks focus on common text cases (e.g., normal size, density) and single scenarios, while ignoring extreme video text challenges, i.e., dense and small text in various scenarios. In this competition report, we establish a video text reading benchmark, DSText, which focuses on dense and small text reading challenges in the video with various scenarios. Compared with the previous datasets, the proposed dataset mainly include three new challenges: 1) Dense video texts, a new challenge for video text spotter. 2) High-proportioned small texts. 3) Various new scenarios, e.g., Game, sports, etc. The proposed DSText includes 100 video clips from 12 open scenarios, supporting two tasks (i.e., video text tracking (Task 1) and end-to-end video text spotting (Task 2)). During the competition period (opened on 15th February 2023 and closed on 20th March 2023), a total of 24 teams participated in the three proposed tasks with around 30 valid submissions, respectively. In this article, we describe detailed statistical information of the dataset, tasks, evaluation protocols and the results summaries of the ICDAR 2023 on DSText competition. Moreover, we hope the benchmark will promise video text research in the community. △ Less

Submitted 10 April, 2023; originally announced April 2023.

Journal ref: ICDAR 2023 competition

A CNN Based Framework for Unistroke Numeral Recognition in Air-Writing

Authors: Prasun Roy, Subhankar Ghosh, Umapada Pal

Abstract: Air-writing refers to virtually writing linguistic characters through hand gestures in three-dimensional space with six degrees of freedom. This paper proposes a generic video camera-aided convolutional neural network (CNN) based air-writing framework. Gestures are performed using a marker of fixed color in front of a generic video camera, followed by color-based segmentation to identify the marke… ▽ More Air-writing refers to virtually writing linguistic characters through hand gestures in three-dimensional space with six degrees of freedom. This paper proposes a generic video camera-aided convolutional neural network (CNN) based air-writing framework. Gestures are performed using a marker of fixed color in front of a generic video camera, followed by color-based segmentation to identify the marker and track the trajectory of the marker tip. A pre-trained CNN is then used to classify the gesture. The recognition accuracy is further improved using transfer learning with the newly acquired data. The performance of the system varies significantly on the illumination condition due to color-based segmentation. In a less fluctuating illumination condition, the system is able to recognize isolated unistroke numerals of multiple languages. The proposed framework has achieved 97.7%, 95.4% and 93.7% recognition rates in person independent evaluations on English, Bengali and Devanagari numerals, respectively. △ Less

Submitted 18 February, 2025; v1 submitted 14 March, 2023; originally announced March 2023.

Comments: Accepted in The International Conference on Frontiers of Handwriting Recognition (ICFHR) 2018

Semantically Consistent Person Image Generation

Authors: Prasun Roy, Saumik Bhattacharya, Subhankar Ghosh, Umapada Pal, Michael Blumenstein

Abstract: We propose a data-driven approach for context-aware person image generation. Specifically, we attempt to generate a person image such that the synthesized instance can blend into a complex scene. In our method, the position, scale, and appearance of the generated person are semantically conditioned on the existing persons in the scene. The proposed technique is divided into three sequential steps.… ▽ More We propose a data-driven approach for context-aware person image generation. Specifically, we attempt to generate a person image such that the synthesized instance can blend into a complex scene. In our method, the position, scale, and appearance of the generated person are semantically conditioned on the existing persons in the scene. The proposed technique is divided into three sequential steps. At first, we employ a Pix2PixHD model to infer a coarse semantic mask that represents the new person's spatial location, scale, and potential pose. Next, we use a data-centric approach to select the closest representation from a precomputed cluster of fine semantic masks. Finally, we adopt a multi-scale, attention-guided architecture to transfer the appearance attributes from an exemplar image. The proposed strategy enables us to synthesize semantically coherent realistic persons that can blend into an existing scene without altering the global context. We conclude our findings with relevant qualitative and quantitative evaluations. △ Less

Submitted 18 February, 2025; v1 submitted 28 February, 2023; originally announced February 2023.

Comments: Accepted in The International Conference on Pattern Recognition (ICPR) 2024

TIC: Text-Guided Image Colorization

Authors: Subhankar Ghosh, Prasun Roy, Saumik Bhattacharya, Umapada Pal, Michael Blumenstein

Abstract: Image colorization is a well-known problem in computer vision. However, due to the ill-posed nature of the task, image colorization is inherently challenging. Though several attempts have been made by researchers to make the colorization pipeline automatic, these processes often produce unrealistic results due to a lack of conditioning. In this work, we attempt to integrate textual descriptions as… ▽ More Image colorization is a well-known problem in computer vision. However, due to the ill-posed nature of the task, image colorization is inherently challenging. Though several attempts have been made by researchers to make the colorization pipeline automatic, these processes often produce unrealistic results due to a lack of conditioning. In this work, we attempt to integrate textual descriptions as an auxiliary condition, along with the grayscale image that is to be colorized, to improve the fidelity of the colorization process. To the best of our knowledge, this is one of the first attempts to incorporate textual conditioning in the colorization pipeline. To do so, we have proposed a novel deep network that takes two inputs (the grayscale image and the respective encoded text description) and tries to predict the relevant color gamut. As the respective textual descriptions contain color information of the objects present in the scene, the text encoding helps to improve the overall quality of the predicted colors. We have evaluated our proposed model using different metrics and found that it outperforms the state-of-the-art colorization algorithms both qualitatively and quantitatively. △ Less

Submitted 4 August, 2022; originally announced August 2022.

TIPS: Text-Induced Pose Synthesis

Authors: Prasun Roy, Subhankar Ghosh, Saumik Bhattacharya, Umapada Pal, Michael Blumenstein

Abstract: In computer vision, human pose synthesis and transfer deal with probabilistic image generation of a person in a previously unseen pose from an already available observation of that person. Though researchers have recently proposed several methods to achieve this task, most of these techniques derive the target pose directly from the desired target image on a specific dataset, making the underlying… ▽ More In computer vision, human pose synthesis and transfer deal with probabilistic image generation of a person in a previously unseen pose from an already available observation of that person. Though researchers have recently proposed several methods to achieve this task, most of these techniques derive the target pose directly from the desired target image on a specific dataset, making the underlying process challenging to apply in real-world scenarios as the generation of the target image is the actual aim. In this paper, we first present the shortcomings of current pose transfer algorithms and then propose a novel text-based pose transfer technique to address those issues. We divide the problem into three independent stages: (a) text to pose representation, (b) pose refinement, and (c) pose rendering. To the best of our knowledge, this is one of the first attempts to develop a text-based pose transfer framework where we also introduce a new dataset DF-PASS, by adding descriptive pose annotations for the images of the DeepFashion dataset. The proposed method generates promising results with significant qualitative and quantitative scores in our experiments. △ Less

Submitted 18 February, 2025; v1 submitted 24 July, 2022; originally announced July 2022.

Comments: Accepted in The European Conference on Computer Vision (ECCV) 2022

SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition

Authors: Dajian Zhong, Shujing Lyu, Palaiahnakote Shivakumara, Bing Yin, Jiajia Wu, Umapada Pal, Yue Lu

Abstract: Scene text recognition is a challenging task due to the complex backgrounds and diverse variations of text instances. In this paper, we propose a novel Semantic GAN and Balanced Attention Network (SGBANet) to recognize the texts in scene images. The proposed method first generates the simple semantic feature using Semantic GAN and then recognizes the scene text with the Balanced Attention Module.… ▽ More Scene text recognition is a challenging task due to the complex backgrounds and diverse variations of text instances. In this paper, we propose a novel Semantic GAN and Balanced Attention Network (SGBANet) to recognize the texts in scene images. The proposed method first generates the simple semantic feature using Semantic GAN and then recognizes the scene text with the Balanced Attention Module. The Semantic GAN aims to align the semantic feature distribution between the support domain and target domain. Different from the conventional image-to-image translation methods that perform at the image level, the Semantic GAN performs the generation and discrimination on the semantic level with the Semantic Generator Module (SGM) and Semantic Discriminator Module (SDM). For target images (scene text images), the Semantic Generator Module generates simple semantic features that share the same feature distribution with support images (clear text images). The Semantic Discriminator Module is used to distinguish the semantic features between the support domain and target domain. In addition, a Balanced Attention Module is designed to alleviate the problem of attention drift. The Balanced Attention Module first learns a balancing parameter based on the visual glimpse vector and semantic glimpse vector, and then performs the balancing operation for obtaining a balanced glimpse vector. Experiments on six benchmarks, including regular datasets, i.e., IIIT5K, SVT, ICDAR2013, and irregular datasets, i.e., ICDAR2015, SVTP, CUTE80, validate the effectiveness of our proposed method. △ Less

Submitted 20 July, 2022; originally announced July 2022.

Comments: Accepted by ECCV 2022

Scene Aware Person Image Generation through Global Contextual Conditioning

Authors: Prasun Roy, Subhankar Ghosh, Saumik Bhattacharya, Umapada Pal, Michael Blumenstein

Abstract: Person image generation is an intriguing yet challenging problem. However, this task becomes even more difficult under constrained situations. In this work, we propose a novel pipeline to generate and insert contextually relevant person images into an existing scene while preserving the global semantics. More specifically, we aim to insert a person such that the location, pose, and scale of the pe… ▽ More Person image generation is an intriguing yet challenging problem. However, this task becomes even more difficult under constrained situations. In this work, we propose a novel pipeline to generate and insert contextually relevant person images into an existing scene while preserving the global semantics. More specifically, we aim to insert a person such that the location, pose, and scale of the person being inserted blends in with the existing persons in the scene. Our method uses three individual networks in a sequential pipeline. At first, we predict the potential location and the skeletal structure of the new person by conditioning a Wasserstein Generative Adversarial Network (WGAN) on the existing human skeletons present in the scene. Next, the predicted skeleton is refined through a shallow linear network to achieve higher structural accuracy in the generated image. Finally, the target image is generated from the refined skeleton using another generative network conditioned on a given image of the target person. In our experiments, we achieve high-resolution photo-realistic generation results while preserving the general context of the scene. We conclude our paper with multiple qualitative and quantitative benchmarks on the results. △ Less

Submitted 18 February, 2025; v1 submitted 6 June, 2022; originally announced June 2022.

Comments: Accepted in The International Conference on Pattern Recognition (ICPR) 2022

SWIS: Self-Supervised Representation Learning For Writer Independent Offline Signature Verification

Authors: Siladittya Manna, Soumitri Chattopadhyay, Saumik Bhattacharya, Umapada Pal

Abstract: Writer independent offline signature verification is one of the most challenging tasks in pattern recognition as there is often a scarcity of training data. To handle such data scarcity problem, in this paper, we propose a novel self-supervised learning (SSL) framework for writer independent offline signature verification. To our knowledge, this is the first attempt to utilize self-supervised sett… ▽ More Writer independent offline signature verification is one of the most challenging tasks in pattern recognition as there is often a scarcity of training data. To handle such data scarcity problem, in this paper, we propose a novel self-supervised learning (SSL) framework for writer independent offline signature verification. To our knowledge, this is the first attempt to utilize self-supervised setting for the signature verification task. The objective of self-supervised representation learning from the signature images is achieved by minimizing the cross-covariance between two random variables belonging to different feature directions and ensuring a positive cross-covariance between the random variables denoting the same feature direction. This ensures that the features are decorrelated linearly and the redundant information is discarded. Through experimental results on different data sets, we obtained encouraging results. △ Less

Submitted 12 July, 2022; v1 submitted 26 February, 2022; originally announced February 2022.

Comments: Accepted at IEEE ICIP 2022

Multi-scale Attention Guided Pose Transfer

Authors: Prasun Roy, Saumik Bhattacharya, Subhankar Ghosh, Umapada Pal

Abstract: Pose transfer refers to the probabilistic image generation of a person with a previously unseen novel pose from another image of that person having a different pose. Due to potential academic and commercial applications, this problem is extensively studied in recent years. Among the various approaches to the problem, attention guided progressive generation is shown to produce state-of-the-art resu… ▽ More Pose transfer refers to the probabilistic image generation of a person with a previously unseen novel pose from another image of that person having a different pose. Due to potential academic and commercial applications, this problem is extensively studied in recent years. Among the various approaches to the problem, attention guided progressive generation is shown to produce state-of-the-art results in most cases. In this paper, we present an improved network architecture for pose transfer by introducing attention links at every resolution level of the encoder and decoder. By utilizing such dense multi-scale attention guided approach, we are able to achieve significant improvement over the existing methods both visually and analytically. We conclude our findings with extensive qualitative and quantitative comparisons against several existing methods on the DeepFashion dataset. △ Less

Submitted 18 February, 2025; v1 submitted 14 February, 2022; originally announced February 2022.

Comments: Accepted in Pattern Recognition (PR) 2023

DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer

Authors: Sanket Biswas, Ayan Banerjee, Josep Lladós, Umapada Pal

Abstract: Understanding documents with rich layouts is an essential step towards information extraction. Business intelligence processes often require the extraction of useful semantic content from documents at a large scale for subsequent decision-making tasks. In this context, instance-level segmentation of different document objects (title, sections, figures etc.) has emerged as an interesting problem fo… ▽ More Understanding documents with rich layouts is an essential step towards information extraction. Business intelligence processes often require the extraction of useful semantic content from documents at a large scale for subsequent decision-making tasks. In this context, instance-level segmentation of different document objects (title, sections, figures etc.) has emerged as an interesting problem for the document analysis and understanding community. To advance the research in this direction, we present a transformer-based model called \emph{DocSegTr} for end-to-end instance segmentation of complex layouts in document images. The method adapts a twin attention module, for semantic reasoning, which helps to become highly computationally efficient compared with the state-of-the-art. To the best of our knowledge, this is the first work on transformer-based document segmentation. Extensive experimentation on competitive benchmarks like PubLayNet, PRIMA, Historical Japanese (HJ) and TableBank demonstrate that our model achieved comparable or better segmentation performance than the existing state-of-the-art approaches with the average precision of 89.4, 40.3, 83.4 and 93.3. This simple and flexible framework could serve as a promising baseline for instance-level recognition tasks in document images. △ Less

Submitted 21 September, 2022; v1 submitted 27 January, 2022; originally announced January 2022.

Comments: Preprint

DocEnTr: An End-to-End Document Image Enhancement Transformer

Authors: Mohamed Ali Souibgui, Sanket Biswas, Sana Khamekhem Jemni, Yousri Kessentini, Alicia Fornés, Josep Lladós, Umapada Pal

Abstract: Document images can be affected by many degradation scenarios, which cause recognition and processing difficulties. In this age of digitization, it is important to denoise them for proper usage. To address this challenge, we present a new encoder-decoder architecture based on vision transformers to enhance both machine-printed and handwritten document images, in an end-to-end fashion. The encoder… ▽ More Document images can be affected by many degradation scenarios, which cause recognition and processing difficulties. In this age of digitization, it is important to denoise them for proper usage. To address this challenge, we present a new encoder-decoder architecture based on vision transformers to enhance both machine-printed and handwritten document images, in an end-to-end fashion. The encoder operates directly on the pixel patches with their positional information without the use of any convolutional layers, while the decoder reconstructs a clean image from the encoded patches. Conducted experiments show a superiority of the proposed model compared to the state-of the-art methods on several DIBCO benchmarks. Code and models will be publicly available at: \url{https://github.com/dali92002/DocEnTR}. △ Less

Submitted 25 January, 2022; originally announced January 2022.

Comments: submitted to ICPR 2022

SURDS: Self-Supervised Attention-guided Reconstruction and Dual Triplet Loss for Writer Independent Offline Signature Verification

Authors: Soumitri Chattopadhyay, Siladittya Manna, Saumik Bhattacharya, Umapada Pal

Abstract: Offline Signature Verification (OSV) is a fundamental biometric task across various forensic, commercial and legal applications. The underlying task at hand is to carefully model fine-grained features of the signatures to distinguish between genuine and forged ones, which differ only in minute deformities. This makes OSV more challenging compared to other verification problems. In this work, we pr… ▽ More Offline Signature Verification (OSV) is a fundamental biometric task across various forensic, commercial and legal applications. The underlying task at hand is to carefully model fine-grained features of the signatures to distinguish between genuine and forged ones, which differ only in minute deformities. This makes OSV more challenging compared to other verification problems. In this work, we propose a two-stage deep learning framework that leverages self-supervised representation learning as well as metric learning for writer-independent OSV. First, we train an image reconstruction network using an encoder-decoder architecture that is augmented by a 2D spatial attention mechanism using signature image patches. Next, the trained encoder backbone is fine-tuned with a projector head using a supervised metric learning framework, whose objective is to optimize a novel dual triplet loss by sampling negative samples from both within the same writer class as well as from other writers. The intuition behind this is to ensure that a signature sample lies closer to its positive counterpart compared to negative samples from both intra-writer and cross-writer sets. This results in robust discriminative learning of the embedding space. To the best of our knowledge, this is the first work of using self-supervised learning frameworks for OSV. The proposed two-stage framework has been evaluated on two publicly available offline signature datasets and compared with various state-of-the-art methods. It is noted that the proposed method provided promising results outperforming several existing pieces of work. The code is publicly available at: https://github.com/soumitri2001/SURDS-SSL-OSV △ Less

Submitted 26 June, 2022; v1 submitted 25 January, 2022; originally announced January 2022.

Comments: Accepted at ICPR 2022

MIO : Mutual Information Optimization using Self-Supervised Binary Contrastive Learning

Authors: Siladittya Manna, Umapada Pal, Saumik Bhattacharya

Abstract: Self-supervised contrastive learning frameworks have progressed rapidly over the last few years. In this paper, we propose a novel loss function for contrastive learning. We model our pre-training task as a binary classification problem to induce an implicit contrastive effect. We further improve the näive loss function after removing the effect of the positive-positive repulsion and incorporating… ▽ More Self-supervised contrastive learning frameworks have progressed rapidly over the last few years. In this paper, we propose a novel loss function for contrastive learning. We model our pre-training task as a binary classification problem to induce an implicit contrastive effect. We further improve the näive loss function after removing the effect of the positive-positive repulsion and incorporating the upper bound of the negative pair repulsion. Unlike existing methods, the proposed loss function optimizes the mutual information in positive and negative pairs. We also present a closed-form expression for the parameter gradient flow and compare the behaviour of self-supervised contrastive frameworks using Hessian eigenspectrum to analytically study their convergence. The proposed method outperforms SOTA self-supervised contrastive frameworks on benchmark datasets such as CIFAR-10, CIFAR-100, STL-10, and Tiny-ImageNet. After 200 pretraining epochs with ResNet-18 as the backbone, the proposed model achieves an accuracy of 86.36%, 58.18%, 80.50%, and 30.87% on the CIFAR-10, CIFAR-100, STL-10, and Tiny-ImageNet datasets, respectively, and surpasses the SOTA contrastive baseline by 1.93%, 3.57%, 4.85%, and 0.33%, respectively. The proposed framework also achieves a state-of-the-art accuracy of 78.4% (200 epochs) and 65.22% (100 epochs) Top-1 Linear Evaluation accuracy on ImageNet100 and ImageNet1K datasets, respectively. △ Less

Submitted 14 April, 2025; v1 submitted 24 November, 2021; originally announced November 2021.

PAANet: Progressive Alternating Attention for Automatic Medical Image Segmentation

Authors: Abhishek Srivastava, Sukalpa Chanda, Debesh Jha, Michael A. Riegler, Pål Halvorsen, Dag Johansen, Umapada Pal

Abstract: Medical image segmentation can provide detailed information for clinical analysis which can be useful for scenarios where the detailed location of a finding is important. Knowing the location of disease can play a vital role in treatment and decision-making. Convolutional neural network (CNN) based encoder-decoder techniques have advanced the performance of automated medical image segmentation sys… ▽ More Medical image segmentation can provide detailed information for clinical analysis which can be useful for scenarios where the detailed location of a finding is important. Knowing the location of disease can play a vital role in treatment and decision-making. Convolutional neural network (CNN) based encoder-decoder techniques have advanced the performance of automated medical image segmentation systems. Several such CNN-based methodologies utilize techniques such as spatial- and channel-wise attention to enhance performance. Another technique that has drawn attention in recent years is residual dense blocks (RDBs). The successive convolutional layers in densely connected blocks are capable of extracting diverse features with varied receptive fields and thus, enhancing performance. However, consecutive stacked convolutional operators may not necessarily generate features that facilitate the identification of the target structures. In this paper, we propose a progressive alternating attention network (PAANet). We develop progressive alternating attention dense (PAAD) blocks, which construct a guiding attention map (GAM) after every convolutional layer in the dense blocks using features from all scales. The GAM allows the following layers in the dense blocks to focus on the spatial locations relevant to the target region. Every alternate PAAD block inverts the GAM to generate a reverse attention map which guides ensuing layers to extract boundary and edge-related information, refining the segmentation process. Our experiments on three different biomedical image segmentation datasets exhibit that our PAANet achieves favourable performance when compared to other state-of-the-art methods. △ Less

Submitted 20 November, 2021; originally announced November 2021.

GMSRF-Net: An improved generalizability with global multi-scale residual fusion network for polyp segmentation

Authors: Abhishek Srivastava, Sukalpa Chanda, Debesh Jha, Umapada Pal, Sharib Ali

Abstract: Colonoscopy is a gold standard procedure but is highly operator-dependent. Efforts have been made to automate the detection and segmentation of polyps, a precancerous precursor, to effectively minimize missed rate. Widely used computer-aided polyp segmentation systems actuated by encoder-decoder have achieved high performance in terms of accuracy. However, polyp segmentation datasets collected fro… ▽ More Colonoscopy is a gold standard procedure but is highly operator-dependent. Efforts have been made to automate the detection and segmentation of polyps, a precancerous precursor, to effectively minimize missed rate. Widely used computer-aided polyp segmentation systems actuated by encoder-decoder have achieved high performance in terms of accuracy. However, polyp segmentation datasets collected from varied centers can follow different imaging protocols leading to difference in data distribution. As a result, most methods suffer from performance drop and require re-training for each specific dataset. We address this generalizability issue by proposing a global multi-scale residual fusion network (GMSRF-Net). Our proposed network maintains high-resolution representations while performing multi-scale fusion operations for all resolution scales. To further leverage scale information, we design cross multi-scale attention (CMSA) and multi-scale feature selection (MSFS) modules within the GMSRF-Net. The repeated fusion operations gated by CMSA and MSFS demonstrate improved generalizability of the network. Experiments conducted on two different polyp segmentation datasets show that our proposed GMSRF-Net outperforms the previous top-performing state-of-the-art method by 8.34% and 10.31% on unseen CVC-ClinicDB and unseen Kvasir-SEG, in terms of dice coefficient. △ Less

Submitted 20 November, 2021; originally announced November 2021.

Exploiting Multi-Scale Fusion, Spatial Attention and Patch Interaction Techniques for Text-Independent Writer Identification

Authors: Abhishek Srivastava, Sukalpa Chanda, Umapada Pal

Abstract: Text independent writer identification is a challenging problem that differentiates between different handwriting styles to decide the author of the handwritten text. Earlier writer identification relied on handcrafted features to reveal pieces of differences between writers. Recent work with the advent of convolutional neural network, deep learning-based methods have evolved. In this paper, three… ▽ More Text independent writer identification is a challenging problem that differentiates between different handwriting styles to decide the author of the handwritten text. Earlier writer identification relied on handcrafted features to reveal pieces of differences between writers. Recent work with the advent of convolutional neural network, deep learning-based methods have evolved. In this paper, three different deep learning techniques - spatial attention mechanism, multi-scale feature fusion and patch-based CNN were proposed to effectively capture the difference between each writer's handwriting. Our methods are based on the hypothesis that handwritten text images have specific spatial regions which are more unique to a writer's style, multi-scale features propagate characteristic features with respect to individual writers and patch-based features give more general and robust representations that helps to discriminate handwriting from different writers. The proposed methods outperforms various state-of-the-art methodologies on word-level and page-level writer identification methods on three publicly available datasets - CVL, Firemaker, CERUG-EN datasets and give comparable performance on the IAM dataset. △ Less

Submitted 20 November, 2021; originally announced November 2021.

Comments: 14 pages, 4 figures

AGA-GAN: Attribute Guided Attention Generative Adversarial Network with U-Net for Face Hallucination

Authors: Abhishek Srivastava, Sukalpa Chanda, Umapada Pal

Abstract: The performance of facial super-resolution methods relies on their ability to recover facial structures and salient features effectively. Even though the convolutional neural network and generative adversarial network-based methods deliver impressive performances on face hallucination tasks, the ability to use attributes associated with the low-resolution images to improve performance is unsatisfa… ▽ More The performance of facial super-resolution methods relies on their ability to recover facial structures and salient features effectively. Even though the convolutional neural network and generative adversarial network-based methods deliver impressive performances on face hallucination tasks, the ability to use attributes associated with the low-resolution images to improve performance is unsatisfactory. In this paper, we propose an Attribute Guided Attention Generative Adversarial Network which employs novel attribute guided attention (AGA) modules to identify and focus the generation process on various facial features in the image. Stacking multiple AGA modules enables the recovery of both high and low-level facial structures. We design the discriminator to learn discriminative features exploiting the relationship between the high-resolution image and their corresponding facial attribute annotations. We then explore the use of U-Net based architecture to refine existing predictions and synthesize further facial details. Extensive experiments across several metrics show that our AGA-GAN and AGA-GAN+U-Net framework outperforms several other cutting-edge face hallucination state-of-the-art methods. We also demonstrate the viability of our method when every attribute descriptor is not known and thus, establishing its application in real-world scenarios. △ Less

Submitted 20 November, 2021; originally announced November 2021.

Comments: 27 pages, 9 Figures

LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning

Authors: Bhavya Vasudeva, Puneesh Deora, Saumik Bhattacharya, Umapada Pal, Sukalpa Chanda

Abstract: Deep metric learning has been effectively used to learn distance metrics for different visual tasks like image retrieval, clustering, etc. In order to aid the training process, existing methods either use a hard mining strategy to extract the most informative samples or seek to generate hard synthetics using an additional network. Such approaches face different challenges and can lead to biased em… ▽ More Deep metric learning has been effectively used to learn distance metrics for different visual tasks like image retrieval, clustering, etc. In order to aid the training process, existing methods either use a hard mining strategy to extract the most informative samples or seek to generate hard synthetics using an additional network. Such approaches face different challenges and can lead to biased embeddings in the former case, and (i) harder optimization (ii) slower training speed (iii) higher model complexity in the latter case. In order to overcome these challenges, we propose a novel approach that looks for optimal hard negatives (LoOp) in the embedding space, taking full advantage of each tuple by calculating the minimum distance between a pair of positives and a pair of negatives. Unlike mining-based methods, our approach considers the entire space between pairs of embeddings to calculate the optimal hard negatives. Extensive experiments combining our approach and representative metric learning losses reveal a significant boost in performance on three benchmark datasets. △ Less

Submitted 20 August, 2021; originally announced August 2021.

Comments: 17 pages, 9 figures, 5 tables. Accepted at The IEEE/CVF International Conference on Computer Vision (ICCV) 2021

Graph-based Deep Generative Modelling for Document Layout Generation

Authors: Sanket Biswas, Pau Riba, Josep Lladós, Umapada Pal

Abstract: One of the major prerequisites for any deep learning approach is the availability of large-scale training data. When dealing with scanned document images in real world scenarios, the principal information of its content is stored in the layout itself. In this work, we have proposed an automated deep generative model using Graph Neural Networks (GNNs) to generate synthetic data with highly variable… ▽ More One of the major prerequisites for any deep learning approach is the availability of large-scale training data. When dealing with scanned document images in real world scenarios, the principal information of its content is stored in the layout itself. In this work, we have proposed an automated deep generative model using Graph Neural Networks (GNNs) to generate synthetic data with highly variable and plausible document layouts that can be used to train document interpretation systems, in this case, specially in digital mailroom applications. It is also the first graph-based approach for document layout generation task experimented on administrative document images, in this case, invoices. △ Less

Submitted 9 July, 2021; originally announced July 2021.

Comments: Accepted by ICDAR Workshops-GLESDO 2021

DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis

Authors: Sanket Biswas, Pau Riba, Josep Lladós, Umapada Pal

Abstract: Despite significant progress on current state-of-the-art image generation models, synthesis of document images containing multiple and complex object layouts is a challenging task. This paper presents a novel approach, called DocSynth, to automatically synthesize document images based on a given layout. In this work, given a spatial layout (bounding boxes with object categories) as a reference by… ▽ More Despite significant progress on current state-of-the-art image generation models, synthesis of document images containing multiple and complex object layouts is a challenging task. This paper presents a novel approach, called DocSynth, to automatically synthesize document images based on a given layout. In this work, given a spatial layout (bounding boxes with object categories) as a reference by the user, our proposed DocSynth model learns to generate a set of realistic document images consistent with the defined layout. Also, this framework has been adapted to this work as a superior baseline model for creating synthetic document image datasets for augmenting real data during training for document layout analysis tasks. Different sets of learning objectives have been also used to improve the model performance. Quantitatively, we also compare the generated results of our model with real data using standard evaluation metrics. The results highlight that our model can successfully generate realistic and diverse document images with multiple objects. We also present a comprehensive qualitative analysis summary of the different scopes of synthetic image generation tasks. Lastly, to our knowledge this is the first work of its kind. △ Less

Submitted 6 July, 2021; originally announced July 2021.

Comments: Accepted by ICDAR 2021