Removing Undesirable Feature Contributions Using Out-of-Distribution DataDownload PDF

28 Sep 2020 (modified: 03 Mar 2021)ICLR 2021 PosterReaders: Everyone
  • Keywords: adversarial training, adversarial robustness, generalization, out-of-distribution
  • Abstract: Several data augmentation methods deploy unlabeled-in-distribution (UID) data to bridge the gap between the training and inference of neural networks. However, these methods have clear limitations in terms of availability of UID data and dependence of algorithms on pseudo-labels. Herein, we propose a data augmentation method to improve generalization in both adversarial and standard learning by using out-of-distribution (OOD) data that are devoid of the abovementioned issues. We show how to improve generalization theoretically using OOD data in each learning scenario and complement our theoretical analysis with experiments on CIFAR-10, CIFAR-100, and a subset of ImageNet. The results indicate that undesirable features are shared even among image data that seem to have little correlation from a human point of view. We also present the advantages of the proposed method through comparison with other data augmentation methods, which can be used in the absence of UID data. Furthermore, we demonstrate that the proposed method can further improve the existing state-of-the-art adversarial training.
  • One-sentence Summary: We propose a simple method, Out-of-distribution data Augmented Training (OAT), to leverage OOD data for adversarial and standard learning.
  • Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
13 Replies