OpenCoS: Contrastive Semi-supervised Learning for Handling Open-Set Unlabeled Data
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Jongjin | - |
dc.contributor.author | Yun, Sukmin | - |
dc.contributor.author | Jeong, Jongheon | - |
dc.contributor.author | Shin, Jinwoo | - |
dc.date.accessioned | 2024-04-09T03:31:57Z | - |
dc.date.available | 2024-04-09T03:31:57Z | - |
dc.date.issued | 2022-10 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/118656 | - |
dc.description.abstract | Semi-supervised learning (SSL) has been a powerful strategy to incorporate few labels in learning better representations. In this paper, we focus on a practical scenario that one aims to apply SSL when unlabeled data may contain out-of-class samples - those that cannot have one-hot encoded labels from a closed-set of classes in label data, i.e., the unlabeled data is an open-set. Specifically, we introduce OpenCoS, a simple framework for handling this realistic semi-supervised learning scenario based upon a recent framework of self-supervised visual representation learning. We first observe that the out-of-class samples in the open-set unlabeled dataset can be identified effectively via self-supervised contrastive learning. Then, OpenCoS utilizes this information to overcome the failure modes in the existing state-of-the-art semi-supervised methods, by utilizing one-hot pseudo-labels and soft-labels for the identified in- and out-of-class unlabeled data, respectively. Our extensive experimental results show the effectiveness of OpenCoS under the presence of out-of-class samples, fixing up the state-of-the-art semi-supervised methods to be suitable for diverse scenarios involving open-set unlabeled data. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG. | - |
dc.format.extent | 16 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Springer Verlag | - |
dc.title | OpenCoS: Contrastive Semi-supervised Learning for Handling Open-Set Unlabeled Data | - |
dc.type | Article | - |
dc.publisher.location | 미국 | - |
dc.identifier.doi | 10.1007/978-3-031-25063-7_9 | - |
dc.identifier.scopusid | 2-s2.0-85151063081 | - |
dc.identifier.bibliographicCitation | Computer Vision – ECCV 2022 Workshops Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part II, pp 134 - 149 | - |
dc.citation.title | Computer Vision – ECCV 2022 Workshops Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part II | - |
dc.citation.startPage | 134 | - |
dc.citation.endPage | 149 | - |
dc.type.docType | 정기 학술지(note) | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | Class-distribution mismatch | - |
dc.subject.keywordAuthor | Contrastive learning | - |
dc.subject.keywordAuthor | Open-set semi-supervised learning | - |
dc.subject.keywordAuthor | Realistic semi-supervised learning | - |
dc.identifier.url | https://link.springer.com/chapter/10.1007/978-3-031-25063-7_9?utm_source=getftr&utm_medium=getftr&utm_campaign=getftr_pilot | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
55 Hanyangdeahak-ro, Sangnok-gu, Ansan, Gyeonggi-do, 15588, Korea+82-31-400-4269 sweetbrain@hanyang.ac.kr
COPYRIGHT © 2021 HANYANG UNIVERSITY. ALL RIGHTS RESERVED.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.