Robustness and Equivariance of Neural Networks

Sep 27, 2018 ICLR 2019 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: Neural networks models are known to be vulnerable to geometric transformations as well as small pixel-wise perturbations of input. Convolutional Neural Networks (CNNs) are translation-equivariant but can be easily fooled using rotations and small pixel-wise perturbations. Moreover, CNNs require sufficient translations in their training data to achieve translation-invariance. Recent work by Cohen & Welling (2016), Worrall et al. (2016), Kondor & Trivedi (2018), Cohen & Welling (2017), Marcos et al. (2017), and Esteves et al. (2018) has gone beyond translations, and constructed rotation-equivariant or more general group-equivariant neural network models. In this paper, we do an extensive empirical study of various rotation-equivariant neural network models to understand how effectively they learn rotations. This includes Group-equivariant Convolutional Networks (GCNNs) by Cohen & Welling (2016), Harmonic Networks (H-Nets) by Worrall et al. (2016), Polar Transformer Networks (PTN) by Esteves et al. (2018) and Rotation equivariant vector field networks by Marcos et al. (2017). We empirically compare the ability of these networks to learn rotations efficiently in terms of their number of parameters, sample complexity, rotation augmentation used in training. We compare them against each other as well as Standard CNNs. We observe that as these rotation-equivariant neural networks learn rotations, they instead become more vulnerable to small pixel-wise adversarial attacks, e.g., Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD), in comparison with Standard CNNs. In other words, robustness to geometric transformations in these models comes at the cost of robustness to small pixel-wise perturbations.
  • Keywords: robust, adversarial, equivariance, rotations, GCNNs, CNNs, steerable, neural networks
  • TL;DR: Robustness to rotations comes at the cost of robustness of pixel-wise adversarial perturbations.
0 Replies

Loading