Inter-domain curriculum learning for domain generalization
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Daehee | - |
dc.contributor.author | Kim, Jinkyu | - |
dc.contributor.author | Lee, Jaekoo | - |
dc.date.accessioned | 2022-12-09T19:42:46Z | - |
dc.date.available | 2022-12-09T19:42:46Z | - |
dc.date.created | 2022-12-08 | - |
dc.date.issued | 2022-06 | - |
dc.identifier.issn | 2405-9595 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/146634 | - |
dc.description.abstract | Domain generalization aims to learn a domain-invariant representation from multiple source domains so that a model can generalize well across unseen target domains. Such models are often trained with examples that are presented randomly from all source domains, which can make the training unstable due to optimization in conflicting gradient directions. Here, we explore inter-domain curriculum learning (IDCL) where source domains are exposed in a meaningful order to gradually provide more complex ones. The experiments show that significant improvements can be achieved in both PACS and Office-Home benchmarks, and ours improves the state-of-the-art method by 1.08%. (c) 2021 The Author(s). Published by Elsevier B.V. on behalf of The Korean Institute of Communications and Information Sciences. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER | - |
dc.title | Inter-domain curriculum learning for domain generalization | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Jinkyu | - |
dc.identifier.doi | 10.1016/j.icte.2021.11.009 | - |
dc.identifier.scopusid | 2-s2.0-85121099432 | - |
dc.identifier.wosid | 000810442900012 | - |
dc.identifier.bibliographicCitation | ICT EXPRESS, v.8, no.2, pp.225 - 229 | - |
dc.relation.isPartOf | ICT EXPRESS | - |
dc.citation.title | ICT EXPRESS | - |
dc.citation.volume | 8 | - |
dc.citation.number | 2 | - |
dc.citation.startPage | 225 | - |
dc.citation.endPage | 229 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.identifier.kciid | ART002859081 | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.description.journalRegisteredClass | kci | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.subject.keywordAuthor | Domain generalization | - |
dc.subject.keywordAuthor | Inter-domain curriculum learning | - |
dc.subject.keywordAuthor | Deep neural networks | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea 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.