Self-Supervise, Refine, Repeat: Improving Unsupervised Anomaly DetectionDownload PDF

Published: 28 Jan 2022, Last Modified: 13 Feb 2023ICLR 2022 SubmittedReaders: Everyone
Keywords: Anomaly detection, Data refinement, Iterative training
Abstract: Anomaly detection (AD) - separating anomalies from normal data - has many applications across domains, from manufacturing to healthcare. While most previous works have been shown to be effective for cases with fully or partially labeled data, that setting is in practice less common due to labeling being particularly tedious for this task. In this paper, we focus on fully unsupervised AD, in which the entire training dataset, containing both normal and anomalous samples, is unlabeled. To tackle this problem effectively, we propose to improve the robustness of one-class classification trained on self-supervised representations using a data refinement process. Our proposed data refinement approach is based on an ensemble of one-class classifiers (OCCs), each of which is trained on a disjoint subset of training data. Representations learned by self-supervised learning on the refined data are iteratively updated as the refinement improves. We demonstrate our method on various unsupervised AD tasks with image and tabular data. With a 10% anomaly ratio on CIFAR-10 image data / 2.5% anomaly ratio on Thyroid tabular data, the proposed method outperforms the state-of-the-art one-class classification method by 6.3 AUC and 12.5 average precision / 22.9 F1-score.
12 Replies

Loading