Understanding the Role of Self-Supervised Learning in Out-of-Distribution Detection Task
This provides a guideline for designing better OOD detection algorithms and insights for other tasks where SSL can improve performance, but it is incremental as it builds on existing SSL and OOD detection concepts.
The paper investigates how self-supervised learning (SSL) enhances out-of-distribution (OOD) detection by increasing the overall feature space dimension and potentially shrinking the inlier feature space, making OOD detection easier.
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.