ImageNet-trained {CNN}s are biased towards texture; increasing shape bias improves accuracy and robustness on ShortScience.org

openreview.net
scholar.google.com

ImageNet-trained {CNN}s are biased towards texture; increasing shape bias improves accuracy and robustness
Geirhos, Robert and Rubisch, Patricia and Michaelis, Claudio and Bethge, Matthias and Wichmann, Felix A. and Brendel, Wieland
International Conference on Learning Representations - 2019 via Local Bibsonomy
Keywords: deep-learning, machine-learning, stable, foundations, robustness, theory

Summaries/Notes 1

[link] Summary by David Stutz 5 years ago

Geirhos et al. show that state-of-the-art convolutional neural networks put too much importance on texture information. This claim is confirmed in a controlled study comparing convolutional neural network and human performance on variants of ImageNet image with removed texture (silhouettes) or on edges. Additionally, networks only considering local information can perform nearly as well as other networks. To avoid this bias, they propose a stylized ImageNet variant where textured are replaced randomly, forcing the network to put more weight on global shape information.

Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).

Your comment:

Write your summary here (You can use $\LaTeX$ and markdown syntax):

Anon Private