Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness

May 28, 2019 ICML 2019 Workshop Deep Phenomena Blind Submission readers: everyone
  • Keywords: adversarial training, robustness, spatial transformations, invariance
  • Abstract: This work provides theoretical and empirical evidence that invariance-inducing regularizers can increase predictive accuracy for worst-case spatial transformations (spatial robustness). Evaluated on these adversarially transformed examples, we demonstrate that adding regularization on top of standard or adversarial training reduces the relative error by 20% for CIFAR10 without increasing the computational cost. This outperforms handcrafted networks that were explicitly designed to be spatial-equivariant. Furthermore, we observe for SVHN, known to have inherent variance in orientation, that robust training also improves standard accuracy on the test set.
  • TL;DR: for spatial transformations robust minimizer also minimizes standard accuracy; invariance-inducing regularization leads to better robustness than specialized architectures
0 Replies

Loading