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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?


May 26, 2023
Felix A. Wichmann, Robert Geirhos

Add code

* Preprint version of article accepted by Annual Review of Vision Science (https://www.annualreviews.org/doi/abs/10.1146/annurev-vision-120522-031739). Posted with permission from the Annual Review of Vision Science, Volume 9 by Annual Reviews, http://www.annualreviews.org 

   Access Paper or Ask Questions

Scaling Vision Transformers to 22 Billion Parameters


Feb 10, 2023
Mostafa Dehghani, Josip Djolonga, Basil Mustafa, Piotr Padlewski, Jonathan Heek, Justin Gilmer, Andreas Steiner, Mathilde Caron, Robert Geirhos, Ibrahim Alabdulmohsin, Rodolphe Jenatton, Lucas Beyer, Michael Tschannen, Anurag Arnab, Xiao Wang, Carlos Riquelme, Matthias Minderer, Joan Puigcerver, Utku Evci, Manoj Kumar, Sjoerd van Steenkiste, Gamaleldin F. Elsayed, Aravindh Mahendran, Fisher Yu, Avital Oliver, Fantine Huot, Jasmijn Bastings, Mark Patrick Collier, Alexey Gritsenko, Vighnesh Birodkar, Cristina Vasconcelos, Yi Tay, Thomas Mensink, Alexander Kolesnikov, Filip Pavetić, Dustin Tran, Thomas Kipf, Mario Lučić, Xiaohua Zhai, Daniel Keysers, Jeremiah Harmsen, Neil Houlsby

Add code


   Access Paper or Ask Questions

Beyond neural scaling laws: beating power law scaling via data pruning


Jun 29, 2022
Ben Sorscher, Robert Geirhos, Shashank Shekhar, Surya Ganguli, Ari S. Morcos

Add code


   Access Paper or Ask Questions

The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networks


May 20, 2022
Lukas S. Huber, Robert Geirhos, Felix A. Wichmann

Add code

* Manuscript under review at Journal of Vision 

   Access Paper or Ask Questions

Trivial or impossible -- dichotomous data difficulty masks model differences (on ImageNet and beyond)


Oct 12, 2021
Kristof Meding, Luca M. Schulze Buschoff, Robert Geirhos, Felix A. Wichmann

Add code

* Under review as a conference paper at ICLR 2022 

   Access Paper or Ask Questions

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

Add code

* 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

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

Add code

* 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

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

Add code


   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

Add code


   Access Paper or Ask Questions

Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency


Jun 30, 2020
Robert Geirhos, Kristof Meding, Felix A. Wichmann

Add code


   Access Paper or Ask Questions

1
2
>>