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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Increasing Confidence in Adversarial Robustness Evaluations


Jun 28, 2022
Roland S. Zimmermann, Wieland Brendel, Florian Tramer, Nicholas Carlini

* Oral at CVPR 2022 Workshop (Art of Robustness). Project website https://zimmerrol.github.io/active-tests/ 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Embrace the Gap: VAEs Perform Independent Mechanism Analysis


Jun 06, 2022
Patrik Reizinger, Luigi Gresele, Jack Brady, Julius von Kügelgen, Dominik Zietlow, Bernhard Schölkopf, Georg Martius, Wieland Brendel, Michel Besserve

* 41 pages, under review 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Visual Representation Learning Does Not Generalize Strongly Within the Same Domain


Jul 23, 2021
Lukas Schott, Julius von Kügelgen, Frederik Träuble, Peter Gehler, Chris Russell, Matthias Bethge, Bernhard Schölkopf, Francesco Locatello, Wieland Brendel


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

How Well do Feature Visualizations Support Causal Understanding of CNN Activations?


Jun 23, 2021
Roland S. Zimmermann, Judy Borowski, Robert Geirhos, Matthias Bethge, Thomas S. A. Wallis, Wieland Brendel

* ICML 2021 XAI workshop version. Joint first and last authors. Project website at https://brendel-group.github.io/causal-understanding-via-visualizations/ 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Partial success in closing the gap between human and machine vision


Jun 14, 2021
Robert Geirhos, Kantharaju Narayanappa, Benjamin Mitzkus, Tizian Thieringer, Matthias Bethge, Felix A. Wichmann, Wieland Brendel

* A preliminary version of this work was presented as Oral at the 2020 NeurIPS workshop on "Shared Visual Representations in Human & Machine Intelligence" (arXiv:2010.08377) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style


Jun 08, 2021
Julius von Kügelgen, Yash Sharma, Luigi Gresele, Wieland Brendel, Bernhard Schölkopf, Michel Besserve, Francesco Locatello


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Adapting ImageNet-scale models to complex distribution shifts with self-learning


Apr 28, 2021
Evgenia Rusak, Steffen Schneider, Peter Gehler, Oliver Bringmann, Wieland Brendel, Matthias Bethge

* Web: https://domainadaptation.org/selflearning 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints


Feb 25, 2021
Maura Pintor, Fabio Roli, Wieland Brendel, Battista Biggio


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Contrastive Learning Inverts the Data Generating Process


Feb 17, 2021
Roland S. Zimmermann, Yash Sharma, Steffen Schneider, Matthias Bethge, Wieland Brendel

* The first three authors, as well as the last two authors, contributed equally. Code is available at https://brendel-group.github.io/cl-ica 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>