Robert Geirhos | DeepAI

DeepAI AI Chat

Featured Co-authors

Matthias Bethge
63 publications
Richard Zemel
59 publications
Surya Ganguli
56 publications
Neil Houlsby
44 publications
Mostafa Dehghani
43 publications
Been Kim
42 publications
Mario Lucic
40 publications
Wieland Brendel
37 publications
Ari S. Morcos
28 publications
Basil Mustafa
22 publications
Shashank Shekhar
21 publications

∙ 07/12/2023

Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

The ubiquitous and demonstrably suboptimal choice of resizing images to ...

0 Mostafa Dehghani, et al. ∙

∙ 06/07/2023

Don't trust your eyes: on the (un)reliability of feature visualizations

How do neural networks extract patterns from pixels? Feature visualizati...

0 Robert Geirhos, et al. ∙

∙ 05/26/2023

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

Deep neural networks (DNNs) are machine learning algorithms that have re...

0 Felix A. Wichmann, et al. ∙

∙ 06/29/2022

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

Widely observed neural scaling laws, in which error falls off as a power...

12 Ben Sorscher, et al. ∙

∙ 05/20/2022

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

In laboratory object recognition tasks based on undistorted photographs,...

14 Lukas S. Huber, et al. ∙

∙ 10/12/2021

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

"The power of a generalization system follows directly from its biases" ...

0 Kristof Meding, et al. ∙

∙ 06/23/2021

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

One widely used approach towards understanding the inner workings of dee...

26 Roland S. Zimmermann, et al. ∙

∙ 06/14/2021

Partial success in closing the gap between human and machine vision

A few years ago, the first CNN surpassed human performance on ImageNet. ...

0 Robert Geirhos, et al. ∙

∙ 10/23/2020

Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations

Feature visualizations such as synthetic maximally activating images are...

13 Judy Borowski, et al. ∙

∙ 10/16/2020

On the surprising similarities between supervised and self-supervised models

How do humans learn to acquire a powerful, flexible and robust represent...

0 Robert Geirhos, et al. ∙

∙ 06/30/2020

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

A central problem in cognitive science and behavioural neuroscience as w...

0 Robert Geirhos, et al. ∙

∙ 04/16/2020

Shortcut Learning in Deep Neural Networks

Deep learning has triggered the current rise of artificial intelligence ...

3 Robert Geirhos, et al. ∙

∙ 07/17/2019

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

The ability to detect objects regardless of image distortions or weather...

4 Claudio Michaelis, et al. ∙

∙ 11/29/2018

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

Convolutional Neural Networks (CNNs) are commonly thought to recognise o...

14 Robert Geirhos, et al. ∙

∙ 08/27/2018

Generalisation in humans and deep neural networks

We compare the robustness of humans and current convolutional deep neura...

4 Robert Geirhos, et al. ∙

∙ 06/21/2017

Comparing deep neural networks against humans: object recognition when the signal gets weaker

Human visual object recognition is typically rapid and seemingly effortl...

0 Robert Geirhos, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world