Publications
Detailed Information
Masked Contrastive Learning for Anomaly Detection
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cho, Hyunsoo | - |
dc.contributor.author | Seol, Jinseok | - |
dc.contributor.author | Lee, Sang-Goo | - |
dc.date.accessioned | 2022-06-24T00:25:50Z | - |
dc.date.available | 2022-06-24T00:25:50Z | - |
dc.date.created | 2022-05-02 | - |
dc.date.issued | 2021-08 | - |
dc.identifier.citation | IJCAI International Joint Conference on Artificial Intelligence, pp.1434-1441 | - |
dc.identifier.issn | 1045-0823 | - |
dc.identifier.uri | https://hdl.handle.net/10371/183730 | - |
dc.description.abstract | © 2021 International Joint Conferences on Artificial Intelligence. All rights reserved.Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demonstrated their efficiencies. In particular, self-supervised learning based methods are spurring interest due to their capability of learning diverse representations without additional labels. Among self-supervised learning tactics, contrastive learning is one specific framework validating their superiority in various fields, including anomaly detection. However, the primary objective of contrastive learning is to learn task-agnostic features without any labels, which is not entirely suited to discern anomalies. In this paper, we propose a task-specific variant of contrastive learning named masked contrastive learning, which is more befitted for anomaly detection. Moreover, we propose a new inference method dubbed self-ensemble inference that further boosts performance by leveraging the ability learned through auxiliary self-supervision tasks. By combining our models, we can outperform previous state-of-the-art methods by a significant margin on various benchmark datasets. | - |
dc.language | 영어 | - |
dc.publisher | IJCAI International Joint Conference on Artificial Intelligence | - |
dc.title | Masked Contrastive Learning for Anomaly Detection | - |
dc.type | Article | - |
dc.identifier.doi | 10.48550/arXiv.2105.08793 | - |
dc.citation.journaltitle | IJCAI International Joint Conference on Artificial Intelligence | - |
dc.identifier.scopusid | 2-s2.0-85123408511 | - |
dc.citation.endpage | 1441 | - |
dc.citation.startpage | 1434 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Lee, Sang-Goo | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.