Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWMSchwerpunkte/Kompetenzen
- Computer Vision
- Adversarial Robustness
- Signal Processing fundamentals for CNNs
Publikationen
Highlightpublikationen
- Grabinski, J., Gavrikov, P., Keuper, J., & Keuper, M. (2022). Robust Models are less Over-Confident. Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS) 2022. https://arxiv.org/abs/2210.05938
- Grabinski, J., Jung, S., Keuper, J., & Keuper, M. (2022). FrequencyLowCut Pooling--Plug & Play against Catastrophic Overfitting. European Conference on Computer Vision (ECCV) 2022. https://arxiv.org/abs/2204.00491
- Grabinski, J., Keuper, J., & Keuper, M. (2022). Aliasing and adversarial robust generalization of CNNs. European Convference on Machine Learning (ECML) 2022, Machine Learning, 1-27. https://link.springer.com/article/10.1007/s10994-022-06222-8