Classification-Based Anomaly Detection for General DataDownload PDF

25 Sept 2019, 19:30 (modified: 10 Feb 2022, 11:44)ICLR 2020 Conference Blind SubmissionReaders: Everyone
Original Pdf: pdf
Data: [CIFAR-10](, [CIFAR-100](
TL;DR: Anomaly detection method that uses: openset techniques for better generalization, random-transformation classification for non-image data.
Abstract: Anomaly detection, finding patterns that substantially deviate from those seen previously, is one of the fundamental problems of artificial intelligence. Recently, classification-based methods were shown to achieve superior results on this task. In this work, we present a unifying view and propose an open-set method, GOAD, to relax current generalization assumptions. Furthermore, we extend the applicability of transformation-based methods to non-image data using random affine transformations. Our method is shown to obtain state-of-the-art accuracy and is applicable to broad data types. The strong performance of our method is extensively validated on multiple datasets from different domains.
Keywords: anomaly detection
9 Replies