-
Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations
Feature visualizations such as synthetic maximally activating images are...
10/23/2020 ∙ by Judy Borowski, et al. ∙
13
∙
share
read it
-
On the surprising similarities between supervised and self-supervised models
How do humans learn to acquire a powerful, flexible and robust represent...
10/16/2020 ∙ by Robert Geirhos, et al. ∙
0
∙
share
read it
-
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...
06/30/2020 ∙ by Robert Geirhos, et al. ∙
0
∙
share
read it
-
Shortcut Learning in Deep Neural Networks
Deep learning has triggered the current rise of artificial intelligence ...
04/16/2020 ∙ by Robert Geirhos, et al. ∙
3
∙
share
read it
-
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming
The ability to detect objects regardless of image distortions or weather...
07/17/2019 ∙ by Claudio Michaelis, et al. ∙
4
∙
share
read it
-
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
Convolutional Neural Networks (CNNs) are commonly thought to recognise o...
11/29/2018 ∙ by Robert Geirhos, et al. ∙
14
∙
share
read it
-
Generalisation in humans and deep neural networks
We compare the robustness of humans and current convolutional deep neura...
08/27/2018 ∙ by Robert Geirhos, et al. ∙
4
∙
share
read it
-
Comparing deep neural networks against humans: object recognition when the signal gets weaker
Human visual object recognition is typically rapid and seemingly effortl...
06/21/2017 ∙ by Robert Geirhos, et al. ∙
0
∙
share
read it
