Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Beluch, William"'
Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolving content. They tend to synthesize quasi-static videos, ignoring the n
Externí odkaz:
http://arxiv.org/abs/2403.13501
Within the context of autonomous driving, encountering unknown objects becomes inevitable during deployment in the open world. Therefore, it is crucial to equip standard semantic segmentation models with anomaly awareness. Many previous approaches ha
Externí odkaz:
http://arxiv.org/abs/2308.09965
Many natural language processing (NLP) tasks are naturally imbalanced, as some target categories occur much more frequently than others in the real world. In such scenarios, current NLP models still tend to perform poorly on less frequent classes. Ad
Externí odkaz:
http://arxiv.org/abs/2210.04675
Object type classification for automotive radar has greatly improved with recent deep learning (DL) solutions, however these developments have mostly focused on the classification accuracy. Before employing DL solutions in safety-critical application
Externí odkaz:
http://arxiv.org/abs/2109.12851
Autor:
Eulig, Elias, Saranrittichai, Piyapat, Mummadi, Chaithanya Kumar, Rambach, Kilian, Beluch, William, Shi, Xiahan, Fischer, Volker
Publikováno v:
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 10655-10664
Common deep neural networks (DNNs) for image classification have been shown to rely on shortcut opportunities (SO) in the form of predictive and easy-to-represent visual factors. This is known as shortcut learning and leads to impaired generalization
Externí odkaz:
http://arxiv.org/abs/2108.05779
Autor:
Patel, Kanil, Beluch, William, Rambach, Kilian, Cozma, Adriana-Eliza, Pfeiffer, Michael, Yang, Bin
Publikováno v:
IEEE Radar Conference 2021
Deep learning (DL) has recently attracted increasing interest to improve object type classification for automotive radar.In addition to high accuracy, it is crucial for decision making in autonomous vehicles to evaluate the reliability of the predict
Externí odkaz:
http://arxiv.org/abs/2106.05870
Post-hoc multi-class calibration is a common approach for providing high-quality confidence estimates of deep neural network predictions. Recent work has shown that widely used scaling methods underestimate their calibration error, while alternative
Externí odkaz:
http://arxiv.org/abs/2006.13092
Uncertainty estimates help to identify ambiguous, novel, or anomalous inputs, but the reliable quantification of uncertainty has proven to be challenging for modern deep networks. In order to improve uncertainty estimation, we propose On-Manifold Adv
Externí odkaz:
http://arxiv.org/abs/1912.07458
Deep neural networks (DNNs) are powerful tools in computer vision tasks. However, in many realistic scenarios label noise is prevalent in the training images, and overfitting to these noisy labels can significantly harm the generalization performance
Externí odkaz:
http://arxiv.org/abs/1906.11876
Many natural language processing (NLP) tasks are naturally imbalanced, as some target categories occur much more frequently than others in the real world. In such scenarios, current NLP models still tend to perform poorly on less frequent classes. Ad
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::db5b16c7deeaf0019e6316ab6ea39f16
https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/105561
https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/105561