Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Closing the Generalization Gap in One-Shot Object Detection

Nov 09, 2020
Claudio Michaelis, Matthias Bethge, Alexander S. Ecker


  Access Paper or Ask Questions

Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations

Oct 23, 2020
Judy Borowski, Roland S. Zimmermann, Judith Schepers, Robert Geirhos, Thomas S. A. Wallis, Matthias Bethge, Wieland Brendel


  Access Paper or Ask Questions

On the surprising similarities between supervised and self-supervised models

Oct 16, 2020
Robert Geirhos, Kantharaju Narayanappa, Benjamin Mitzkus, Matthias Bethge, Felix A. Wichmann, Wieland Brendel


  Access Paper or Ask Questions

EagerPy: Writing Code That Works Natively with PyTorch, TensorFlow, JAX, and NumPy

Aug 10, 2020
Jonas Rauber, Matthias Bethge, Wieland Brendel


  Access Paper or Ask Questions

Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding

Jul 21, 2020
David Klindt, Lukas Schott, Yash Sharma, Ivan Ustyuzhaninov, Wieland Brendel, Matthias Bethge, Dylan Paiton

* Code is available at https://github.com/bethgelab/slow_disentanglement. The first three authors, as well as the last two authors, contributed equally 

  Access Paper or Ask Questions

Fast Differentiable Clipping-Aware Normalization and Rescaling

Jul 15, 2020
Jonas Rauber, Matthias Bethge


  Access Paper or Ask Questions

Improving robustness against common corruptions by covariate shift adaptation

Jun 30, 2020
Steffen Schneider, Evgenia Rusak, Luisa Eck, Oliver Bringmann, Wieland Brendel, Matthias Bethge


  Access Paper or Ask Questions

Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences

Jun 12, 2020
Marissa A. Weis, Kashyap Chitta, Yash Sharma, Wieland Brendel, Matthias Bethge, Andreas Geiger, Alexander S. Ecker


  Access Paper or Ask Questions

Shortcut Learning in Deep Neural Networks

May 20, 2020
Robert Geirhos, Jörn-Henrik Jacobsen, Claudio Michaelis, Richard Zemel, Wieland Brendel, Matthias Bethge, Felix A. Wichmann

* perspective article 

  Access Paper or Ask Questions

Towards causal generative scene models via competition of experts

Apr 27, 2020
Julius von Kügelgen, Ivan Ustyuzhaninov, Peter Gehler, Matthias Bethge, Bernhard Schölkopf

* Presented at the ICLR 2020 workshop "Causal learning for decision making" 

  Access Paper or Ask Questions

The Notorious Difficulty of Comparing Human and Machine Perception

Apr 20, 2020
Christina M. Funke, Judy Borowski, Karolina Stosio, Wieland Brendel, Thomas S. A. Wallis, Matthias Bethge


  Access Paper or Ask Questions

Increasing the robustness of DNNs against image corruptions by playing the Game of Noise

Feb 26, 2020
Evgenia Rusak, Lukas Schott, Roland S. Zimmermann, Julian Bitterwolf, Oliver Bringmann, Matthias Bethge, Wieland Brendel


  Access Paper or Ask Questions

Learning From Brains How to Regularize Machines

Nov 11, 2019
Zhe Li, Wieland Brendel, Edgar Y. Walker, Erick Cobos, Taliah Muhammad, Jacob Reimer, Matthias Bethge, Fabian H. Sinz, Xaq Pitkow, Andreas S. Tolias

* 14 pages, 7 figures, NeurIPS 2019 

  Access Paper or Ask Questions

Pretraining boosts out-of-domain robustness for pose estimation

Sep 24, 2019
Alexander Mathis, Mert Yüksekgönül, Byron Rogers, Matthias Bethge, Mackenzie W. Mathis


  Access Paper or Ask Questions

Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming

Jul 17, 2019
Claudio Michaelis, Benjamin Mitzkus, Robert Geirhos, Evgenia Rusak, Oliver Bringmann, Alexander S. Ecker, Matthias Bethge, Wieland Brendel

* 23 pages, 10 figures, 1 dragon 

  Access Paper or Ask Questions

Accurate, reliable and fast robustness evaluation

Jul 01, 2019
Wieland Brendel, Jonas Rauber, Matthias Kümmerer, Ivan Ustyuzhaninov, Matthias Bethge


  Access Paper or Ask Questions

Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet

Mar 20, 2019
Wieland Brendel, Matthias Bethge

* Published as a conference paper at the Seventh International Conference on Learning Representations (ICLR 2019) 

  Access Paper or Ask Questions

ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness

Nov 29, 2018
Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A. Wichmann, Wieland Brendel

* Under review at ICLR 2019 (review scores 8,8,7) 

  Access Paper or Ask Questions

One-Shot Instance Segmentation

Nov 28, 2018
Claudio Michaelis, Ivan Ustyuzhaninov, Matthias Bethge, Alexander S. Ecker


  Access Paper or Ask Questions

Excessive Invariance Causes Adversarial Vulnerability

Nov 01, 2018
Jörn-Henrik Jacobsen, Jens Behrmann, Richard Zemel, Matthias Bethge


  Access Paper or Ask Questions

A rotation-equivariant convolutional neural network model of primary visual cortex

Sep 27, 2018
Alexander S. Ecker, Fabian H. Sinz, Emmanouil Froudarakis, Paul G. Fahey, Santiago A. Cadena, Edgar Y. Walker, Erick Cobos, Jacob Reimer, Andreas S. Tolias, Matthias Bethge


  Access Paper or Ask Questions

Towards the first adversarially robust neural network model on MNIST

Sep 20, 2018
Lukas Schott, Jonas Rauber, Matthias Bethge, Wieland Brendel


  Access Paper or Ask Questions

Generalisation in humans and deep neural networks

Aug 27, 2018
Robert Geirhos, Carlos R. Medina Temme, Jonas Rauber, Heiko H. Schuett, Matthias Bethge, Felix A. Wichmann

* Submitted to NIPS 2018. 26 pages, 14 figures, 1 table. Supersedes and greatly extends arXiv:1706.06969 

  Access Paper or Ask Questions

Adversarial Vision Challenge

Aug 06, 2018
Wieland Brendel, Jonas Rauber, Alexey Kurakin, Nicolas Papernot, Behar Veliqi, Marcel Salathé, Sharada P. Mohanty, Matthias Bethge

* https://www.crowdai.org/challenges/adversarial-vision-challenge 

  Access Paper or Ask Questions

Diverse feature visualizations reveal invariances in early layers of deep neural networks

Jul 27, 2018
Santiago A. Cadena, Marissa A. Weis, Leon A. Gatys, Matthias Bethge, Alexander S. Ecker

* Accepted for ECCV 2018 

  Access Paper or Ask Questions

Saliency Benchmarking Made Easy: Separating Models, Maps and Metrics

Jul 25, 2018
Matthias Kümmerer, Thomas S. A. Wallis, Matthias Bethge

* published at ECCV 2018 

  Access Paper or Ask Questions