2021/10/26 by Jiuhai Chen, Chen Zhu, Chen, Jiuhai +3
Computer Science · Engineering · Mathematics · #Anomaly Detection Techniques and Applications #Anomaly detection #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Dimension (graph theory) #Domain Adaptation and Few-Shot Learning #Engineering #FOS: Computer and information sciences #Feature (linguistics) #Feature extraction #Feature vector #Machine Learning (cs.LG) #Machine Learning and ELM #Machine learning #Mathematics #Outlier #Pattern recognition (psychology) #Point (geometry) #Space (punctuation) #Task (project management) #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2110.13435
published in arXiv (Cornell University) (Cornell University)
arxiv created 2021/10/26 · openalex publication_date 2021/10/26 · arxiv updated 2021/10/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.