Inspect, understand, overcome: A survey of practical methods for ai safety S Houben, S Abrecht, M Akila, A Bär, F Brockherde, P Feifel, ... Deep Neural Networks and Data for Automated Driving: Robustness, Uncertainty …, 2022 | 55 | 2022 |
Using ontologies for dataset engineering in automotive AI applications M Herrmann, C Witt, L Lake, S Guneshka, C Heinzemann, F Bonarens, ... 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE), 526-531, 2022 | 14 | 2022 |
Identifikation und Behandlung von Ausreißern in Flugbetriebsdaten für Machine Learning Modelle S Baumann, M Gnisia, P Feifel, U Klingauf Deutsche Gesellschaft für Luft-und Raumfahrt-Lilienthal-Oberth eV, 2018 | 7 | 2018 |
Reevaluating the safety impact of inherent interpretability on deep neural networks for pedestrian detection P Feifel, F Bonarens, F Koster Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2021 | 4 | 2021 |
Leveraging interpretability: Concept-based pedestrian detection with deep neural networks P Feifel, F Bonarens, F Köster Proceedings of the 5th ACM Computer Science in Cars Symposium, 1-10, 2021 | 1 | 2021 |
Domain Adaptive Pedestrian Detection Based on Semantic Concepts P Feifel, F Bonarens, F Köster VISIGRAPP/ VISAPP, 2023 | | 2023 |
Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection P Feifel, B Franke, A Raulf, F Schwenker, F Bonarens, F Köster Proceedings of IJCAI-ECAI Workshop on Artificial Intelligence Safety, 2022 | | 2022 |