Classification-Based Anomaly Detection for General Data.

Liron Bergman, Yedid Hoshen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.
Original languageEnglish
Title of host publicationICLR 2020
Subtitle of host publicationInternational Conference on Learning Representations
PublisherOpenReview
Number of pages10
StatePublished - 2020
EventInternational Conference on Learning Representations, ICLR 2020
- Virtual event
Duration: 26 Apr 20201 May 2020
https://iclr.cc/Conferences/2020

Conference

ConferenceInternational Conference on Learning Representations, ICLR 2020
Abbreviated titleICLR 2020
Period26/04/201/05/20
Internet address

Keywords

  • Anomaly detection

Fingerprint

Dive into the research topics of 'Classification-Based Anomaly Detection for General Data.'. Together they form a unique fingerprint.

Cite this