Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
Abstract
Self-supervision provides effective representations for downstream tasks without requiring labels. However, existing approaches lag behind fully supervised training and are often not thought beneficial beyond obviating or reducing the need for annotations. We find that self-supervision can benefit robustness in a variety of ways, including robustness to adversarial examples, label corruption, and common input corruptions. Additionally, self-supervision greatly benefits out-of-distribution detection on difficult, near-distribution outliers, so much so that it exceeds the performance of fully supervised methods. These results demonstrate the promise of self-supervision for improving robustness and uncertainty estimation and establish these tasks as new axes of evaluation for future self-supervised learning research.
Cite
@article{arxiv.1906.12340,
title = {Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty},
author = {Dan Hendrycks and Mantas Mazeika and Saurav Kadavath and Dawn Song},
journal= {arXiv preprint arXiv:1906.12340},
year = {2019}
}
Comments
NeurIPS 2019; code and data available at https://github.com/hendrycks/ss-ood