Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–10 of 10 results for author: Gawlikowski, J

Searching in archive cs. Search in all archives.
.
  1. arXiv:2608.16614  [pdf, ps, other

    cs.CV

    Beyond Accuracy: Assessing Calibration of Geospatial Foundation Models and Their Sensitivity to Distribution Shifts

    Authors: Nils Lehmann, Jakob Gawlikowski, Burak Ekim, Isaac Corley, Xiao Xiang Zhu

    Abstract: Geospatial Foundation Models (GeoFMs) are most commonly ranked and selected by accuracy on standard benchmark conditions via averaged ranks. We show that this protocol is too narrow: the promised deployment in critical EO tasks requires further angles of analysis, mainly calibration, the agreement between a model's confidence and its correctness. Across 16 frozen encoders, four classification and… ▽ More

    Submitted 17 August, 2026; originally announced August 2026.

  2. arXiv:2607.22408  [pdf, ps, other

    cs.LG

    LunarFM: A Shared Multimodal Representation of the Moon's Surface

    Authors: Marc Girona-Mata, Jakob Gawlikowski, Sumit Goski, Gautier Bardi de Fourtou, Valentin T. Bickel, Ben Moseley, Abigail Calzada-Diaz, Sylvester Kaczmarek, Raúl Ramos-Pollán

    Abstract: The renewed global focus on lunar exploration, driven by the prospect of in-situ resource utilization and a sustained human presence on the Moon, has created growing demand for accurate, large-scale characterization of the lunar surface. Although vast quantities of orbital remote-sensing data have been collected, scientific analysis and resource mapping remain fragmented by heterogeneous multiinst… ▽ More

    Submitted 24 July, 2026; originally announced July 2026.

    Comments: 19 pages, 12 figures

  3. arXiv:2603.00604  [pdf, ps, other

    cs.CV

    Data-Centric Benchmark for Label Noise Estimation and Ranking in Remote Sensing Image Segmentation

    Authors: Keiller Nogueira, Codrut-Andrei Diaconu, Dávid Kerekes, Jakob Gawlikowski, Cédric Léonard, Nassim Ait Ali Braham, June Moh Goo, Zichao Zeng, Zhipeng Liu, Pallavi Jain, Andrea Nascetti, Ronny Hänsch

    Abstract: High-quality pixel-level annotations are essential for the semantic segmentation of remote sensing imagery. However, such labels are expensive to obtain and often affected by noise due to the labor-intensive and time-consuming nature of pixel-wise annotation, which makes it challenging for human annotators to label every pixel accurately. Annotation errors can significantly degrade the performance… ▽ More

    Submitted 28 February, 2026; originally announced March 2026.

  4. arXiv:2410.17832  [pdf, other

    cs.CV

    Exploiting Text-Image Latent Spaces for the Description of Visual Concepts

    Authors: Laines Schmalwasser, Jakob Gawlikowski, Joachim Denzler, Julia Niebling

    Abstract: Concept Activation Vectors (CAVs) offer insights into neural network decision-making by linking human friendly concepts to the model's internal feature extraction process. However, when a new set of CAVs is discovered, they must still be translated into a human understandable description. For image-based neural networks, this is typically done by visualizing the most relevant images of a CAV, whil… ▽ More

    Submitted 23 October, 2024; originally announced October 2024.

    Comments: 19 pages, 7 figures, to be published in ICPR

  5. arXiv:2410.03390  [pdf, other

    cs.CV cs.LG

    Lightning UQ Box: A Comprehensive Framework for Uncertainty Quantification in Deep Learning

    Authors: Nils Lehmann, Jakob Gawlikowski, Adam J. Stewart, Vytautas Jancauskas, Stefan Depeweg, Eric Nalisnick, Nina Maria Gottschling

    Abstract: Uncertainty quantification (UQ) is an essential tool for applying deep neural networks (DNNs) to real world tasks, as it attaches a degree of confidence to DNN outputs. However, despite its benefits, UQ is often left out of the standard DNN workflow due to the additional technical knowledge required to apply and evaluate existing UQ procedures. Hence there is a need for a comprehensive toolbox tha… ▽ More

    Submitted 4 October, 2024; originally announced October 2024.

    Comments: 10 pages, 8 figures

  6. Unraveling Anomalies in Time: Unsupervised Discovery and Isolation of Anomalous Behavior in Bio-regenerative Life Support System Telemetry

    Authors: Ferdinand Rewicki, Jakob Gawlikowski, Julia Niebling, Joachim Denzler

    Abstract: The detection of abnormal or critical system states is essential in condition monitoring. While much attention is given to promptly identifying anomalies, a retrospective analysis of these anomalies can significantly enhance our comprehension of the underlying causes of observed undesired behavior. This aspect becomes particularly critical when the monitored system is deployed in a vital environme… ▽ More

    Submitted 26 September, 2024; v1 submitted 14 June, 2024; originally announced June 2024.

    Comments: 12 pages, + Supplemental Materials, Published at Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track. ECML PKDD 2024

    Journal ref: Lecture Notes in Computer Science, vol. 14949 (2024) 207-222

  7. arXiv:2205.10060  [pdf, other

    cs.LG cs.NE stat.ML

    The Unreasonable Effectiveness of Deep Evidential Regression

    Authors: Nis Meinert, Jakob Gawlikowski, Alexander Lavin

    Abstract: There is a significant need for principled uncertainty reasoning in machine learning systems as they are increasingly deployed in safety-critical domains. A new approach with uncertainty-aware regression-based neural networks (NNs), based on learning evidential distributions for aleatoric and epistemic uncertainties, shows promise over traditional deterministic methods and typical Bayesian NNs, no… ▽ More

    Submitted 16 July, 2023; v1 submitted 20 May, 2022; originally announced May 2022.

    Comments: 11 pages, 25 figures

    Journal ref: AAAI, vol. 37, no. 8, pp. 9134-9142, Jun. 2023

  8. arXiv:2107.03342  [pdf, other

    cs.LG stat.ML

    A Survey of Uncertainty in Deep Neural Networks

    Authors: Jakob Gawlikowski, Cedrique Rovile Njieutcheu Tassi, Mohsin Ali, Jongseok Lee, Matthias Humt, Jianxiang Feng, Anna Kruspe, Rudolph Triebel, Peter Jung, Ribana Roscher, Muhammad Shahzad, Wen Yang, Richard Bamler, Xiao Xiang Zhu

    Abstract: Due to their increasing spread, confidence in neural network predictions became more and more important. However, basic neural networks do not deliver certainty estimates or suffer from over or under confidence. Many researchers have been working on understanding and quantifying uncertainty in a neural network's prediction. As a result, different types and sources of uncertainty have been identifi… ▽ More

    Submitted 18 January, 2022; v1 submitted 7 July, 2021; originally announced July 2021.

  9. arXiv:2107.01557  [pdf, other

    cs.LG cs.AI

    Leveraging Graph and Deep Learning Uncertainties to Detect Anomalous Trajectories

    Authors: Sandeep Kumar Singh, Jaya Shradha Fowdur, Jakob Gawlikowski, Daniel Medina

    Abstract: Understanding and representing traffic patterns are key to detecting anomalous trajectories in the transportation domain. However, some trajectories can exhibit heterogeneous maneuvering characteristics despite confining to normal patterns. Thus, we propose a novel graph-based trajectory representation and association scheme for extraction and confederation of traffic movement patterns, such that… ▽ More

    Submitted 12 March, 2022; v1 submitted 4 July, 2021; originally announced July 2021.

    Comments: Under submission in a Journal

  10. arXiv:2104.05442  [pdf, other

    cs.LG cs.CV

    Out-of-distribution detection in satellite image classification

    Authors: Jakob Gawlikowski, Sudipan Saha, Anna Kruspe, Xiao Xiang Zhu

    Abstract: In satellite image analysis, distributional mismatch between the training and test data may arise due to several reasons, including unseen classes in the test data and differences in the geographic area. Deep learning based models may behave in unexpected manner when subjected to test data that has such distributional shifts from the training data, also called out-of-distribution (OOD) examples. P… ▽ More

    Submitted 9 April, 2021; originally announced April 2021.