Why relu networks yield high-confidence predictions far away from the training data and how to mitigate the problem M Hein, M Andriushchenko, J Bitterwolf Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2019 | 613 | 2019 |
A simple way to make neural networks robust against diverse image corruptions E Rusak, L Schott, RS Zimmermann, J Bitterwolf, O Bringmann, M Bethge, ... Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23 …, 2020 | 213 | 2020 |
Certifiably adversarially robust detection of out-of-distribution data J Bitterwolf, A Meinke, M Hein Advances in Neural Information Processing Systems 33, 16085-16095, 2020 | 78 | 2020 |
Increasing the robustness of dnns against im-age corruptions by playing the game of noise E Rusak, L Schott, R Zimmermann, J Bitterwolfb, O Bringmann, M Bethge, ... | 51 | 2020 |
In or out? fixing imagenet out-of-distribution detection evaluation J Bitterwolf, M Mueller, M Hein arXiv preprint arXiv:2306.00826, 2023 | 48 | 2023 |
Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities J Bitterwolf, A Meinke, M Augustin, M Hein International Conference on Machine Learning, 2041-2074, 2022 | 26 | 2022 |
Provably Robust Detection of Out-of-distribution Data (almost) for free A Meinke, J Bitterwolf, M Hein arXiv preprint arXiv:2106.04260, 2021 | 23 | 2021 |
Provably adversarially robust detection of out-of-distribution data (almost) for free A Meinke, J Bitterwolf, M Hein Advances in Neural Information Processing Systems 35, 30167-30180, 2022 | 4 | 2022 |
Classifiers should do well even on their worst classes J Bitterwolf, A Meinke, V Boreiko, M Hein ICML 2022 Shift Happens Workshop, 2022 | 4 | 2022 |
Neural Network Heuristic Functions: Taking Confidence into Account D Heller, P Ferber, J Bitterwolf, M Hein, J Hoffmann Proceedings of the International Symposium on Combinatorial Search 15 (1 …, 2022 | 2 | 2022 |
Revisiting out-of-distribution detection: A simple baseline is surprisingly effective J Bitterwolf, A Meinke, M Augustin, M Hein | 2 | 2022 |
In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation M Hein, M Müller, J Bitterwolf arXiv, 2023 | | 2023 |
An Artificial Neural Network for Automated Fault Detection E Rusak, J Bitterwolf, S Reiter, A Viehl, O Bringmann Информационные технологии интеллектуальной поддержки принятия решений (ITIDS …, 2018 | | 2018 |