Showing 1–9 of 9 results for author: Yousefi, F

Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation

Authors: Zhihua Liu, Amrutha Saseendran, Lei Tong, Xilin He, Fariba Yousefi, Nikolay Burlutskiy, Dino Oglic, Tom Diethe, Philip Teare, Huiyu Zhou, Chen Jin

Abstract: Open-set image segmentation poses a significant challenge because existing methods often demand extensive training or fine-tuning and generally struggle to segment unified objects consistently across diverse text reference expressions. Motivated by this, we propose Segment Anyword, a novel training-free visual concept prompt learning approach for open-set language grounded segmentation that relies… ▽ More Open-set image segmentation poses a significant challenge because existing methods often demand extensive training or fine-tuning and generally struggle to segment unified objects consistently across diverse text reference expressions. Motivated by this, we propose Segment Anyword, a novel training-free visual concept prompt learning approach for open-set language grounded segmentation that relies on token-level cross-attention maps from a frozen diffusion model to produce segmentation surrogates or mask prompts, which are then refined into targeted object masks. Initial prompts typically lack coherence and consistency as the complexity of the image-text increases, resulting in suboptimal mask fragments. To tackle this issue, we further introduce a novel linguistic-guided visual prompt regularization that binds and clusters visual prompts based on sentence dependency and syntactic structural information, enabling the extraction of robust, noise-tolerant mask prompts, and significant improvements in segmentation accuracy. The proposed approach is effective, generalizes across different open-set segmentation tasks, and achieves state-of-the-art results of 52.5 (+6.8 relative) mIoU on Pascal Context 59, 67.73 (+25.73 relative) cIoU on gRefCOCO, and 67.4 (+1.1 relative to fine-tuned methods) mIoU on GranDf, which is the most complex open-set grounded segmentation task in the field. △ Less

Submitted 23 May, 2025; originally announced May 2025.

MiceBoneChallenge: Micro-CT public dataset and six solutions for automatic growth plate detection in micro-CT mice bone scans

Authors: Nikolay Burlutskiy, Marija Kekic, Jordi de la Torre, Philipp Plewa, Mehdi Boroumand, Julia Jurkowska, Borjan Venovski, Maria Chiara Biagi, Yeman Brhane Hagos, Roksana Malinowska-Traczyk, Yibo Wang, Jacek Zalewski, Paula Sawczuk, Karlo Pintarić, Fariba Yousefi, Leif Hultin

Abstract: Detecting and quantifying bone changes in micro-CT scans of rodents is a common task in preclinical drug development studies. However, this task is manual, time-consuming and subject to inter- and intra-observer variability. In 2024, Anonymous Company organized an internal challenge to develop models for automatic bone quantification. We prepared and annotated a high-quality dataset of 3D $μ$CT bo… ▽ More Detecting and quantifying bone changes in micro-CT scans of rodents is a common task in preclinical drug development studies. However, this task is manual, time-consuming and subject to inter- and intra-observer variability. In 2024, Anonymous Company organized an internal challenge to develop models for automatic bone quantification. We prepared and annotated a high-quality dataset of 3D $μ$CT bone scans from $83$ mice. The challenge attracted over $80$ AI scientists from around the globe who formed $23$ teams. The participants were tasked with developing a solution to identify the plane where the bone growth happens, which is essential for fully automatic segmentation of trabecular bone. As a result, six computer vision solutions were developed that can accurately identify the location of the growth plate plane. The solutions achieved the mean absolute error of $1.91\pm0.87$ planes from the ground truth on the test set, an accuracy level acceptable for practical use by a radiologist. The annotated 3D scans dataset along with the six solutions and source code, is being made public, providing researchers with opportunities to develop and benchmark their own approaches. The code, trained models, and the data will be shared. △ Less

Submitted 26 November, 2024; originally announced November 2024.

Comments: Under Review

Lung tumor segmentation in MRI mice scans using 3D nnU-Net with minimum annotations

Authors: Piotr Kaniewski, Fariba Yousefi, Yeman Brhane Hagos, Talha Qaiser, Nikolay Burlutskiy

Abstract: In drug discovery, accurate lung tumor segmentation is an important step for assessing tumor size and its progression using \textit{in-vivo} imaging such as MRI. While deep learning models have been developed to automate this process, the focus has predominantly been on human subjects, neglecting the pivotal role of animal models in pre-clinical drug development. In this work, we focus on optimizi… ▽ More In drug discovery, accurate lung tumor segmentation is an important step for assessing tumor size and its progression using \textit{in-vivo} imaging such as MRI. While deep learning models have been developed to automate this process, the focus has predominantly been on human subjects, neglecting the pivotal role of animal models in pre-clinical drug development. In this work, we focus on optimizing lung tumor segmentation in mice. First, we demonstrate that the nnU-Net model outperforms the U-Net, U-Net3+, and DeepMeta models. Most importantly, we achieve better results with nnU-Net 3D models than 2D models, indicating the importance of spatial context for segmentation tasks in MRI mice scans. This study demonstrates the importance of 3D input over 2D input images for lung tumor segmentation in MRI scans. Finally, we outperform the prior state-of-the-art approach that involves the combined segmentation of lungs and tumors within the lungs. Our work achieves comparable results using only lung tumor annotations requiring fewer annotations, saving time and annotation efforts. This work (https://anonymous.4open.science/r/lung-tumour-mice-mri-64BB) is an important step in automating pre-clinical animal studies to quantify the efficacy of experimental drugs, particularly in assessing tumor changes. △ Less

Submitted 8 November, 2024; v1 submitted 1 November, 2024; originally announced November 2024.

Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?

Authors: Che Liu, Zhongwei Wan, Haozhe Wang, Yinda Chen, Talha Qaiser, Chen Jin, Fariba Yousefi, Nikolay Burlutskiy, Rossella Arcucci

Abstract: Medical Vision-Language Pre-training (MedVLP) has made significant progress in enabling zero-shot tasks for medical image understanding. However, training MedVLP models typically requires large-scale datasets with paired, high-quality image-text data, which are scarce in the medical domain. Recent advancements in Large Language Models (LLMs) and diffusion models have made it possible to generate l… ▽ More Medical Vision-Language Pre-training (MedVLP) has made significant progress in enabling zero-shot tasks for medical image understanding. However, training MedVLP models typically requires large-scale datasets with paired, high-quality image-text data, which are scarce in the medical domain. Recent advancements in Large Language Models (LLMs) and diffusion models have made it possible to generate large-scale synthetic image-text pairs. This raises the question: "Can MedVLP succeed using purely synthetic data?" To address this, we use off-the-shelf generative models to create synthetic radiology reports and paired Chest X-ray (CXR) images, and propose an automated pipeline to build a diverse, high-quality synthetic dataset, enabling a rigorous study that isolates model and training settings, focusing entirely from the data perspective. Our results show that MedVLP models trained exclusively on synthetic data outperform those trained on real data by 3.8% in averaged AUC on zero-shot classification. Moreover, using a combination of synthetic and real data leads to a further improvement of 9.07%. Additionally, MedVLP models trained on synthetic or mixed data consistently outperform those trained on real data in zero-shot grounding, as well as in fine-tuned classification and segmentation tasks. Our analysis suggests MedVLP trained on well-designed synthetic data can outperform models trained on real datasets, which may be limited by low-quality samples and long-tailed distributions. △ Less

Submitted 25 February, 2025; v1 submitted 17 October, 2024; originally announced October 2024.

Comments: Under Review

ROAD: The ROad event Awareness Dataset for Autonomous Driving

Authors: Gurkirt Singh, Stephen Akrigg, Manuele Di Maio, Valentina Fontana, Reza Javanmard Alitappeh, Suman Saha, Kossar Jeddisaravi, Farzad Yousefi, Jacob Culley, Tom Nicholson, Jordan Omokeowa, Salman Khan, Stanislao Grazioso, Andrew Bradley, Giuseppe Di Gironimo, Fabio Cuzzolin

Abstract: Humans drive in a holistic fashion which entails, in particular, understanding dynamic road events and their evolution. Injecting these capabilities in autonomous vehicles can thus take situational awareness and decision making closer to human-level performance. To this purpose, we introduce the ROad event Awareness Dataset (ROAD) for Autonomous Driving, to our knowledge the first of its kind. ROA… ▽ More Humans drive in a holistic fashion which entails, in particular, understanding dynamic road events and their evolution. Injecting these capabilities in autonomous vehicles can thus take situational awareness and decision making closer to human-level performance. To this purpose, we introduce the ROad event Awareness Dataset (ROAD) for Autonomous Driving, to our knowledge the first of its kind. ROAD is designed to test an autonomous vehicle's ability to detect road events, defined as triplets composed by an active agent, the action(s) it performs and the corresponding scene locations. ROAD comprises videos originally from the Oxford RobotCar Dataset annotated with bounding boxes showing the location in the image plane of each road event. We benchmark various detection tasks, proposing as a baseline a new incremental algorithm for online road event awareness termed 3D-RetinaNet. We also report the performance on the ROAD tasks of Slowfast and YOLOv5 detectors, as well as that of the winners of the ICCV2021 ROAD challenge, which highlight the challenges faced by situation awareness in autonomous driving. ROAD is designed to allow scholars to investigate exciting tasks such as complex (road) activity detection, future event anticipation and continual learning. The dataset is available at https://github.com/gurkirt/road-dataset; the baseline can be found at https://github.com/gurkirt/3D-RetinaNet. △ Less

Submitted 1 April, 2022; v1 submitted 23 February, 2021; originally announced February 2021.

Comments: 29 pages, accepted at TPAMI

Journal ref: TPAMI.2022.3150906

Convening during COVID-19: Lessons learnt from organizing virtual workshops in 2020

Authors: Mandana Samiei, Caroline Weis, Larissa Schiavo, Tatjana Chavdarova, Fariba Yousefi

Abstract: This report is an account of the authors' experiences as organizers of WiML's "Un-Workshop" event at ICML 2020. Un-workshops focus on participant-driven structured discussions on a pre-selected topic. For clarity, this event was different from the "WiML Workshop", which is usually co-located with NeurIPS. In this manuscript, organizers, share their experiences with the hope that it will help futur… ▽ More This report is an account of the authors' experiences as organizers of WiML's "Un-Workshop" event at ICML 2020. Un-workshops focus on participant-driven structured discussions on a pre-selected topic. For clarity, this event was different from the "WiML Workshop", which is usually co-located with NeurIPS. In this manuscript, organizers, share their experiences with the hope that it will help future organizers to host a successful virtual event under similar conditions. Women in Machine Learning (WiML)'s mission is creating connections within a small community of women working in machine learning, in order to encourage mentorship, networking, and interchange of ideas and increase the impact of women in the community. △ Less

Submitted 27 November, 2020; originally announced December 2020.

Comments: 12 pages

Multi-task Learning for Aggregated Data using Gaussian Processes

Authors: Fariba Yousefi, Michael Thomas Smith, Mauricio A. Álvarez

Abstract: Aggregated data is commonplace in areas such as epidemiology and demography. For example, census data for a population is usually given as averages defined over time periods or spatial resolutions (cities, regions or countries). In this paper, we present a novel multi-task learning model based on Gaussian processes for joint learning of variables that have been aggregated at different input scales… ▽ More Aggregated data is commonplace in areas such as epidemiology and demography. For example, census data for a population is usually given as averages defined over time periods or spatial resolutions (cities, regions or countries). In this paper, we present a novel multi-task learning model based on Gaussian processes for joint learning of variables that have been aggregated at different input scales. Our model represents each task as the linear combination of the realizations of latent processes that are integrated at a different scale per task. We are then able to compute the cross-covariance between the different tasks either analytically or numerically. We also allow each task to have a potentially different likelihood model and provide a variational lower bound that can be optimised in a stochastic fashion making our model suitable for larger datasets. We show examples of the model in a synthetic example, a fertility dataset, and an air pollution prediction application. △ Less

Submitted 19 February, 2020; v1 submitted 22 June, 2019; originally announced June 2019.

VeriVANca: An Actor-Based Framework for Formal Verification of Warning Message Dissemination Schemes in VANETs

Authors: Farnaz Yousefi, Ehsan Khamespanah, Mohammed Gharib, Marjan Sirjani, Ali Movaghar

Abstract: One of the applications of vehicular ad-hoc networks is warning message dissemination among vehicles in dangerous situations to prevent more damage. The only communication mechanism for message dissemination is multi-hop broadcast; in which, forwarding a received message have to be regulated using a scheme regarding the selection of forwarding nodes. When analyzing these schemes, simulation-based… ▽ More One of the applications of vehicular ad-hoc networks is warning message dissemination among vehicles in dangerous situations to prevent more damage. The only communication mechanism for message dissemination is multi-hop broadcast; in which, forwarding a received message have to be regulated using a scheme regarding the selection of forwarding nodes. When analyzing these schemes, simulation-based frameworks fail to provide guaranteed analysis results due to the high level of concurrency in this application. Therefore, there is a need to use model checking approaches for achieving reliable results. In this paper, we have developed a framework called VeriVANca, to provide model checking facilities for the analysis of warning message dissemination schemes in VANETs. To this end, an actor-based modeling language, Rebeca, is used which is equipped with a variety of model checking engines. To illustrate the applicability of VeriVANca, modeling and analysis of two warning message dissemination schemes are presented. Some scenarios for these schemes are presented to show that concurrent behaviors of the system components may cause uncertainty in both behavior and performance which may not be detected by simulation-based techniques. Furthermore, the scalability of VeriVANca is examined by analyzing a middle-sized model. △ Less

Submitted 16 April, 2019; originally announced May 2019.

Unsupervised Learning with Imbalanced Data via Structure Consolidation Latent Variable Model

Authors: Fariba Yousefi, Zhenwen Dai, Carl Henrik Ek, Neil Lawrence

Abstract: Unsupervised learning on imbalanced data is challenging because, when given imbalanced data, current model is often dominated by the major category and ignores the categories with small amount of data. We develop a latent variable model that can cope with imbalanced data by dividing the latent space into a shared space and a private space. Based on Gaussian Process Latent Variable Models, we propo… ▽ More Unsupervised learning on imbalanced data is challenging because, when given imbalanced data, current model is often dominated by the major category and ignores the categories with small amount of data. We develop a latent variable model that can cope with imbalanced data by dividing the latent space into a shared space and a private space. Based on Gaussian Process Latent Variable Models, we propose a new kernel formulation that enables the separation of latent space and derives an efficient variational inference method. The performance of our model is demonstrated with an imbalanced medical image dataset. △ Less

Submitted 30 June, 2016; originally announced July 2016.

Comments: ICLR 2016 Workshop