Learning Non-Parametric Surrogate Losses With Correlated Gradients
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yoa, Seungdong | - |
dc.contributor.author | Park, Jinyoung | - |
dc.contributor.author | Kim, Hyunwoo J. | - |
dc.date.accessioned | 2022-03-11T23:40:17Z | - |
dc.date.available | 2022-03-11T23:40:17Z | - |
dc.date.created | 2022-01-20 | - |
dc.date.issued | 2021 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/138652 | - |
dc.description.abstract | Training models by minimizing surrogate loss functions with gradient-based algorithms is a standard approach in various vision tasks. This strategy often leads to suboptimal solutions due to the gap between the target evaluation metrics and surrogate loss functions. In this paper, we propose a framework to learn a surrogate loss function that approximates the evaluation metric with correlated gradients. We observe that the correlated gradients significantly benefit the gradient-based algorithms to improve the quality of solutions. We verify the effectiveness of our method in various tasks such as multi-class classification, ordinal regression, and pose estimation with three evaluation metrics and five datasets. Our extensive experiments showed that our method outperforms conventional loss functions and surrogate loss learning methods. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Learning Non-Parametric Surrogate Losses With Correlated Gradients | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Hyunwoo J. | - |
dc.identifier.doi | 10.1109/ACCESS.2021.3120092 | - |
dc.identifier.scopusid | 2-s2.0-85117762031 | - |
dc.identifier.wosid | 000711696900001 | - |
dc.identifier.bibliographicCitation | IEEE ACCESS, v.9, pp.141199 - 141209 | - |
dc.relation.isPartOf | IEEE ACCESS | - |
dc.citation.title | IEEE ACCESS | - |
dc.citation.volume | 9 | - |
dc.citation.startPage | 141199 | - |
dc.citation.endPage | 141209 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.subject.keywordAuthor | Measurement | - |
dc.subject.keywordAuthor | Task analysis | - |
dc.subject.keywordAuthor | Training | - |
dc.subject.keywordAuthor | Kernel | - |
dc.subject.keywordAuthor | Optimization | - |
dc.subject.keywordAuthor | Loss measurement | - |
dc.subject.keywordAuthor | Pose estimation | - |
dc.subject.keywordAuthor | Learning loss | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | machine learning | - |
dc.subject.keywordAuthor | computer vision | - |
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.