| ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness R Geirhos, P Rubisch, C Michaelis, M Bethge, FA Wichmann, W Brendel Seventh International Conference on Learning Representations (ICLR 2019), 2018 | 546 | 2018 |
| Decision-based adversarial attacks: Reliable attacks against black-box machine learning models W Brendel, J Rauber, M Bethge Sixth International Conference on Learning Representations (ICLR 2018), 2017 | 427 | 2017 |
| Foolbox v0. 8.0: A python toolbox to benchmark the robustness of machine learning models J Rauber, W Brendel, M Bethge Reliable Machine Learning in the Wild Workshop, 34th International …, 2017 | 292* | 2017 |
| On evaluating adversarial robustness N Carlini, A Athalye, N Papernot, W Brendel, J Rauber, D Tsipras, ... arXiv preprint arXiv:1902.06705, 2019 | 241 | 2019 |
| Demixed principal component analysis of neural population data D Kobak, W Brendel, C Constantinidis, CE Feierstein, A Kepecs, ... Elife 5, e10989, 2016 | 218 | 2016 |
| Approximating cnns with bag-of-local-features models works surprisingly well on imagenet W Brendel, M Bethge Seventh International Conference on Learning Representations (ICLR 2019), 2019 | 199 | 2019 |
| Towards the first adversarially robust neural network model on MNIST L Schott, J Rauber, M Bethge, W Brendel Seventh International Conference on Learning Representations (ICLR 2019), 2018 | 158* | 2018 |
| On adaptive attacks to adversarial example defenses F Tramer, N Carlini, W Brendel, A Madry 34th Conference on Neural Information Processing Systems (NeurIPS), 2020 | 76 | 2020 |
| Instanton constituents and fermionic zero modes in twisted CPn models W Brendel, F Bruckmann, L Janssen, A Wipf, C Wozar Physics Letters B 676 (1-3), 116-125, 2009 | 62 | 2009 |
| Shortcut Learning in Deep Neural Networks R Geirhos, JH Jacobsen, C Michaelis, R Zemel, W Brendel, M Bethge, ... Nature Machine Intelligence volume 2, pages665–673(2020), 2020 | 51 | 2020 |
| Demixed principal component analysis W Brendel, R Romo, CK Machens Advances in Neural Information Processing Systems 24 (NIPS 2011), 2654-2662, 2011 | 48 | 2011 |
| Benchmarking robustness in object detection: Autonomous driving when winter is coming C Michaelis, B Mitzkus, R Geirhos, E Rusak, O Bringmann, AS Ecker, ... NeurIPS 2019 Workshop on Machine Learning for Autonomous Driving, 2019 | 41 | 2019 |
| Texture synthesis using shallow convolutional networks with random filters I Ustyuzhaninov, W Brendel, LA Gatys, M Bethge arXiv preprint arXiv:1606.00021, 2016 | 37 | 2016 |
| Adversarial vision challenge W Brendel, J Rauber, A Kurakin, N Papernot, B Veliqi, M Salathé, ... arXiv preprint arXiv:1808.01976, 2018 | 30 | 2018 |
| Increasing the robustness of DNNs against image corruptions by playing the Game of Noise E Rusak, L Schott, R Zimmermann, J Bitterwolf, O Bringmann, M Bethge, ... European Conference on Computer Vision (oral), 2020 | 21 | 2020 |
| Learning to represent signals spike by spike W Brendel, R Bourdoukan, P Vertechi, CK Machens, S Denéve PLoS computational biology 16 (3), e1007692, 2020 | 20 | 2020 |
| What does it take to generate natural textures? I Ustyuzhaninov, W Brendel, LA Gatys, M Bethge International Conference on Learning Representations (ICLR), 2017 | 17 | 2017 |
| Accurate, reliable and fast robustness evaluation W Brendel, J Rauber, M Kümmerer, I Ustyuzhaninov, M Bethge 33rd Conference on Neural Information Processing Systems (NeurIPS), 12841-12851, 2019 | 16 | 2019 |
| Comment on" Biologically inspired protection of deep networks from adversarial attacks" W Brendel, M Bethge arXiv preprint arXiv:1704.01547, 2017 | 14 | 2017 |
| The notorious difficulty of comparing human and machine perception J Borowski, CM Funke, K Stosio, W Brendel, TSA Wallis, M Bethge NeurIPS Workshop: Shared Visual Representations in Human & Machine Intelligence, 2019 | 13* | 2019 |
Matthias BethgeTübingen University & Amazon ScholarVerified email at bethgelab.org
