Data Augmentation is a Hyperparameter: Cherry-picked Self-Supervision for Unsupervised Anomaly Detection is Creating the Illusion of Success

Published: 23 Jul 2023, Last Modified: 26 Jul 2023Accepted by TMLREveryoneRevisionsBibTeX
Abstract: Self-supervised learning (SSL) has emerged as a promising alternative to create supervisory signals to real-world problems, avoiding the extensive cost of manual labeling. SSL is particularly attractive for unsupervised tasks such as anomaly detection (AD), where labeled anomalies are rare or often nonexistent. A large catalog of augmentation functions has been used for SSL-based AD (SSAD) on image data, and recent works have reported that the type of augmentation has a significant impact on accuracy. Motivated by those, this work sets out to put image-based SSAD under a larger lens and investigate the role of data augmentation in SSAD. Through extensive experiments on 3 different detector models and across 420 AD tasks, we provide comprehensive numerical and visual evidences that the alignment between data augmentation and anomaly-generating mechanism is the key to the success of SSAD, and in the lack thereof, SSL may even impair accuracy. To the best of our knowledge, this is the first meta-analysis on the role of data augmentation in SSAD.
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~Charles_Xu1
Submission Number: 1077