Transfer Based Semantic Anomaly Detection

Lucas Deecke, Hakan Bilen, Lukas Ruff, Robert A. Vandermeulen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Detecting semantic anomalies is challenging due to the countless ways in which they may appear in real-world data. While enhancing the robustness of networks may be sufficient for modeling simplistic anomalies, there is no good known way of preparing models for all potential and unseen anomalies that can potentially occur, such as the appearance of new object classes. In this paper, we show that a previously overlooked strategy for anomaly detection (AD) is to introduce an explicit inductive bias toward representations transferred over from some large and varied semantic task. We rigorously verify our hypothesis in controlled trials that utilize intervention, and show that it gives rise to surprisingly effective auxiliary objectives that outperform previous AD paradigms.
Original languageEnglish
Title of host publicationProceedings of the 38th International Conference on Machine Learning
PublisherPMLR
Pages2546-2558
Publication statusPublished - 18 Jul 2021
EventThirty-eighth International Conference on Machine Learning - Online
Duration: 18 Jul 202124 Jul 2021
https://icml.cc/

Publication series

NameProceedings of Machine Learning Research
PublisherPMLR
Volume139
ISSN (Electronic)2640-3498

Conference

ConferenceThirty-eighth International Conference on Machine Learning
Abbreviated titleICML 2021
Period18/07/2124/07/21
Internet address

Fingerprint

Dive into the research topics of 'Transfer Based Semantic Anomaly Detection'. Together they form a unique fingerprint.

Cite this