FrequencyLowCut Pooling--Plug & Play against Catastrophic Overfitting J Grabinski, S Jung, J Keuper, M Keuper Proceedings of the European Conference on Computer Vision (ECCV), 2022 | 10 | 2022 |
Robust Models are less Over-Confident J Grabinski, P Gavrikov, J Keuper, M Keuper Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), 2022 | 9 | 2022 |
Robust models are less over-confident J Grabinski, P Gavrikov, J Keuper, M Keuper The 39th International Conference on Machine Learning (ICML 2022) Workshop …, 2022 | 9 | 2022 |
Aliasing and adversarial robust generalization of CNNs J Grabinski, J Keuper, M Keuper Machine Learning, 1-27, 2022 | 8 | 2022 |
Aliasing coincides with CNNs vulnerability towards adversarial attacks J Grabinski, J Keuper, M Keuper The AAAI-22 Workshop on Adversarial Machine Learning and Beyond, 1-5, 2022 | 4 | 2022 |
On the unreasonable vulnerability of transformers for image restoration-and an easy fix S Agnihotri, KV Gandikota, J Grabinski, P Chandramouli, M Keuper Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023 | 2 | 2023 |
As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain J Grabinski, J Keuper, M Keuper Transactions on Machine Learning Research, 2024 | | 2024 |
Improving Stability during Upsampling--on the Importance of Spatial Context S Agnihotri, J Grabinski, M Keuper arXiv preprint arXiv:2311.17524, 2023 | | 2023 |
Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling J Grabinski, J Keuper, M Keuper arXiv preprint arXiv:2307.09804, 2023 | | 2023 |