English

Achieving Generalizable Robustness of Deep Neural Networks by Stability Training

Machine Learning 2019-11-14 v2 Machine Learning

Abstract

We study the recently introduced stability training as a general-purpose method to increase the robustness of deep neural networks against input perturbations. In particular, we explore its use as an alternative to data augmentation and validate its performance against a number of distortion types and transformations including adversarial examples. In our image classification experiments using ImageNet data stability training performs on a par or even outperforms data augmentation for specific transformations, while consistently offering improved robustness against a broader range of distortion strengths and types unseen during training, a considerably smaller hyperparameter dependence and less potentially negative side effects compared to data augmentation.

Keywords

Cite

@article{arxiv.1906.00735,
  title  = {Achieving Generalizable Robustness of Deep Neural Networks by Stability Training},
  author = {Jan Laermann and Wojciech Samek and Nils Strodthoff},
  journal= {arXiv preprint arXiv:1906.00735},
  year   = {2019}
}

Comments

18 pages, 25 figures; Camera-ready version