Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
This work addresses robustness and uncertainty issues for machine learning practitioners, presenting a novel application of self-supervised learning beyond just reducing annotation needs.
The paper tackles the problem of model robustness and uncertainty by showing that self-supervised learning improves robustness to adversarial examples, label corruption, and input corruptions, and enhances out-of-distribution detection, exceeding fully supervised methods in some cases.
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.