| 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 arXiv preprint arXiv:1811.12231, 2018 | 2879 | 2018 |
| 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 arXiv preprint arXiv:1811.12231, 2018 | 2874 | 2018 |
| Comparison-based framework for psychophysics: Lab versus crowdsourcing S Haghiri, P Rubisch, R Geirhos, F Wichmann, U von Luxburg arXiv preprint arXiv:1905.07234, 2019 | 9 | 2019 |
| Gradient-based learning of compositional dynamics with modular rnns S Otte, P Rubisch, MV Butz Artificial Neural Networks and Machine Learning–ICANN 2019: Theoretical …, 2019 | 8 | 2019 |
| Inducing a human-like shape bias leads to emergent human-level distortion robustness in CNNs R Geirhos, P Rubisch, J Rauber, CRM Temme, C Michaelis, W Brendel, ... Journal of Vision 19 (10), 209c-209c, 2019 | 2 | 2019 |
