2023/06/21 by Jaemin Yoo, Yoo, Jaemin, Lingxiao Zhao +3
Computer Science · Medicine · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Security and Intrusion Detection #Respiratory viral infections research
paper · pdf · doi:10.48550/arxiv.2306.12033
openalex publication_date 2023/06/21 · openalex created_date 2023/06/24 · openalex updated_date 2026/07/28
Self-supervised learning (SSL) has emerged as a promising paradigm that presents supervisory signals to real-world problems, bypassing the extensive cost of manual labeling. Consequently, self-supervised anomaly detection (SSAD) has seen a recent surge of interest, since SSL is especially attractive for unsupervised tasks. However, recent works have reported that the choice of a data augmentation function has significant impact on the accuracy of SSAD, posing augmentation search as an essential but nontrivial problem with the lack of labeled validation data. In this paper, we introduce ST-SSAD, the first systematic approach for rigorous augmentation tuning on SSAD. To this end, our work presents two key contributions. The first is a new unsupervised validation loss that quantifies the alignment between augmented training data and unlabeled validation data. The second is new differentiable augmentation functions, allowing data augmentation hyperparameter(s) to be tuned in an end-to-end manner. Experiments on two testbeds with semantic class anomalies and subtle industrial defects show that ST-SSAD gives significant performance gains over existing works.