Understanding the Role of Self-Supervised Learning in Out-of-Distribution Detection Task

TL;DR

This paper investigates how self-supervised learning enhances out-of-distribution detection by increasing overall feature space and potentially shrinking inlier feature space, providing insights for designing better OOD detectors.

Contribution

It reveals the mechanisms by which SSL improves OOD detection, highlighting the increase in feature space dimension and conditions for shrinking inlier space.

Findings

SSL increases the intrinsic dimension of the overall feature space.

SSL can shrink the inlier feature space under certain conditions.

Enhanced feature space properties facilitate better OOD detection.

Abstract

Self-supervised learning (SSL) has achieved great success in a variety of computer vision tasks. However, the mechanism of how SSL works in these tasks remains a mystery. In this paper, we study how SSL can enhance the performance of the out-of-distribution (OOD) detection task. We first point out two general properties that a good OOD detector should have: 1) the overall feature space should be large and 2) the inlier feature space should be small. Then we demonstrate that SSL can indeed increase the intrinsic dimension of the overall feature space. In the meantime, SSL even has the potential to shrink the inlier feature space. As a result, there will be more space spared for the outliers, making OOD detection much easier. The conditions when SSL can shrink the inlier feature space is also discussed and validated. By understanding the role of SSL in the OOD detection task, our study can provide a guideline for designing better OOD detection algorithms. Moreover, this work can also shed light to other tasks where SSL can improve the performance.