R. Geirhos, J.-H. Jacobsen, C. Michaelis, R. Zemel, W. Brendel, M. Bethge, and F. A. Wichmann
Shortcut Learning in Deep Neural Networks
Nature Machine Intelligence, 2, 665-673, 2020
Code, URL, DOI, BibTex
C. Michaelis, M. Bethge, and A. S. Ecker
Clsoing the Generalization Gap in One-Shot Object Detection
ArXiv, 2020
URL, BibTex
J. Borowski, R. S. Zimmermann, J. Schepers, R. Geirhos, T. S. A. Wallis, M. Bethge, and W. Brendel
Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations
arXiv, 2020
Code, URL, BibTex
J. Rauber, R. Zimmermann, M. Bethge, and W. Brendel
Foolbox Native: Fast adversarial attacks to benchmark the robustness of machine learning models in PyTorch, TensorFlow, and JAX
Journal of Open Source Software, 5(53), 2607, 2020
URL, DOI, BibTex
J. Rauber, M. Bethge, and W. Brendel
EagerPy: Writing Code That Works Natively with PyTorch, TensorFlow, JAX, and NumPy
URL, BibTex
E. Rusak, L. Schott, R. Zimmermann, J. Bitterwolf, O. Bringmann, M. Bethge, and W. Brendel
A simple way to make neural networks robust against diverse image corruptions
European Conference on Computer Vision (ECCV), 2020
URL, BibTex
J. Rauber and M. Bethge
Fast Differentiable Clipping-Aware Normalization and Rescaling
URL, BibTex
D. Klindt, L. Schott, Y. Sharma, I. Ustyuzhaninov, W. Brendel, M. Bethge, and D. Paiton
Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding
arXiv, 2020
#disentanglement, #independent component analysis, #nonlinear, #deep learning, #computer vision, #benchmarking
Code, URL, BibTex
S. Schneider, E. Rusak, L. Eck, O. Bringmann, W. Brendel, and M. Bethge
Removing covariate shift improves robustness against common corruptions
arXiv, 2020
#domain adaptation, #covariate shift, #robustness, #deep learning, #computer vision, #benchmarking
Code, URL, Workshop Paper, BibTex
M. A. Weis, K. Chitta, Y. Sharma, W. Brendel, M. Bethge, A. Geiger, and A. S. Ecker
Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences
arXiv, 2020
Code, URL, BibTex
M. Rolínek, V. Musil, A. Paulus, M. Vlastelica, C. Michaelis, and G. Martius
Optimizing Rank-based Metrics with Blackbox Differentiation
Computer Vision and Pattern Recognition (CVPR), 2020
Code, URL, BibTex
K. J. Sandbrink, P. Mamidanna, C. Michaelis, M. W. Mathis, M. Bethge, and A. Mathis
Task-driven hierarchical deep neural network models of the proprioceptive pathway
bioRxiv, 2020
URL, BibTex
C. M. Funke, J. Borowski, K. Stosio, W. Brendel, T. S. A. Wallis, and M. Bethge
The Notorious Difficulty of Comparing Human and Machine Perception
arXiv (superseded by "Five Points to Check when Comparing Visual Perception in Humans and Machines"), 2020
Code, URL, BibTex
I. Ustyuzhaninov, S. A. Cadena, E. Froudarakis, P. G. Fahey, E. Y. Walker, E. Cobos, J. Reimer, F. H. Sinz, et al.
Rotation-invariant clustering of functional cell types in primary visual cortex
International Conference on Learning Representations (ICLR), 2020
URL, PDF, BibTex
W. Brendel, J. Rauber, A. Kurakin, N. Papernot, B. Veliqi, S. P. Mohanty, F. Laurent, M. Salathé, et al.
Adversarial Vision Challenge (Results)
The NeurIPS'18 Competition, Springer, Cham, 2020, ISBN 978-3-030-29135-8
R. Geirhos, K. Narayanappa, B. Mitzkus, M. Bethge, F. A. Wichmann, and W. Brendel
On the surprising similarities between supervised and self-supervised models
Shared Visual Representations in Humans & Machines Workshop, NeurIPS 2020, 2020
URL, BibTex
K.-K. Lurz, M. Bashiri, K. F. Willeke, A. K. Jagadish, E. Wang, E. Y. Walker, S. Cadena, T. Muhammad, et al.
Generalization in data-driven models of primary visual cortex
bioRxiv, 2020
URL, Code, BibTex
R. Geirhos, K. Meding, and F. A. Wichmann
Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency
Advances in Neural Information Processing Systems 33, 2020
Code, URL, BibTex
Z. Zhao, D. Klindt, A. M. Chagas, K. P. Szatko, L. Rogerson, D. Protti, C. Behrens, D. Dalkara, et al.
The temporal structure of the inner retina at a single glance
Scientific Reports, 2020
#retina, #system identification, #batch effects
URL, BibTex
University of Tuebingen BCCN CIN MPI