Daso: Distribution-aware semantics-oriented pseudo-label for imbalanced semi-supervised learning
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Oh, Youngtaek | - |
dc.contributor.author | Kim, Dong Jin | - |
dc.contributor.author | Kweon, In So | - |
dc.date.accessioned | 2023-08-07T07:50:52Z | - |
dc.date.available | 2023-08-07T07:50:52Z | - |
dc.date.created | 2023-07-20 | - |
dc.date.issued | 2022-06 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/188942 | - |
dc.description.abstract | The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled data. This paper addresses such a relatively under-explored problem. First, we propose a general pseudo-labeling framework that class-adaptively blends the semantic pseudo-label from a similarity-based classifier to the linear one from the linear classifier, after making the observation that both types of pseudo-labels have complementary properties in terms of bias. We further introduce a novel semantic alignment loss to establish balanced feature representation to reduce the biased predictions from the classifier. We term the whole framework as Distribution-Aware Semantics-Oriented (DASO) Pseudo-label. We conduct extensive experiments in a wide range of imbalanced benchmarks: CIFAR10/100-LT, STL10-LT, and large-scale long-tailed Semi-Aves with open-set class, and demonstrate that, the proposed DASO framework reliably improves SSL learners with unlabeled data especially when both (1) class imbalance and (2) distribution mismatch dominate. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE computer society & The computer vision foundation (CVF) | - |
dc.title | Daso: Distribution-aware semantics-oriented pseudo-label for imbalanced semi-supervised learning | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Dong Jin | - |
dc.identifier.doi | 10.1109/CVPR52688.2022.00956 | - |
dc.identifier.scopusid | 2-s2.0-85136128659 | - |
dc.identifier.wosid | 000870759102083 | - |
dc.identifier.bibliographicCitation | Conference on Computer Vision and Pattern Recognition, pp.9776 - 9786 | - |
dc.relation.isPartOf | Conference on Computer Vision and Pattern Recognition | - |
dc.citation.title | Conference on Computer Vision and Pattern Recognition | - |
dc.citation.startPage | 9776 | - |
dc.citation.endPage | 9786 | - |
dc.type.rims | ART | - |
dc.type.docType | Proceeding | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Imaging Science & Photographic Technology | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Imaging Science & Photographic Technology | - |
dc.subject.keywordPlus | Class distributions | - |
dc.subject.keywordPlus | Class imbalance | - |
dc.subject.keywordPlus | Long tail | - |
dc.subject.keywordPlus | Machine-learning | - |
dc.subject.keywordPlus | Oriented distributions | - |
dc.subject.keywordPlus | Real-world | - |
dc.subject.keywordPlus | Self- & | - |
dc.subject.keywordPlus | semi- & | - |
dc.subject.keywordPlus | meta- machine learning | - |
dc.subject.keywordPlus | Semi-supervised learning | - |
dc.subject.keywordPlus | Semi-supervised learning methods | - |
dc.subject.keywordPlus | Transfer/low-shot/long-tail learning | - |
dc.subject.keywordAuthor | Self- & | - |
dc.subject.keywordAuthor | semi- & | - |
dc.subject.keywordAuthor | meta- Machine learning | - |
dc.subject.keywordAuthor | Transfer/low-shot/long-tail learning | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9879221 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
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.