CLC: Noisy Label Correction via Curriculum Learning
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Jaeyoon | - |
dc.contributor.author | Lim, Hyuntak | - |
dc.contributor.author | Chung, Ki-Seok | - |
dc.date.accessioned | 2022-07-06T10:36:02Z | - |
dc.date.available | 2022-07-06T10:36:02Z | - |
dc.date.created | 2022-04-06 | - |
dc.date.issued | 2022-01 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/139750 | - |
dc.description.abstract | Deep neural networks reveal their usefulness through learning from large amounts of data. However, unless the data is correctly labeled, it may be very difficult to properly train a neural network. Labeling the large set of data is a time-consuming and labor-intensive task. To overcome the risk of mislabeling, several methods that are robust against the label noise have been proposed. In this paper, we propose an effective label correction method called Curriculum Label Correction (CLC). With reference to the loss distribution from self-supervised learning, CLC identifies and corrects noisy labels utilizing curriculum learning. Our experimental results verify that CLC shows outstanding performance especially in a harshly noisy condition, 91.06% test accuracy on CIFAR-10 at a noise rate of 0.8. Code is available at https://github.com/LJY-HY/CLC. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE | - |
dc.title | CLC: Noisy Label Correction via Curriculum Learning | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Chung, Ki-Seok | - |
dc.identifier.doi | 10.1109/SSCI50451.2021.9660078 | - |
dc.identifier.scopusid | 2-s2.0-85125812076 | - |
dc.identifier.wosid | 000824464300257 | - |
dc.identifier.bibliographicCitation | 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings, pp.1 - 7 | - |
dc.relation.isPartOf | 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings | - |
dc.citation.title | 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings | - |
dc.citation.startPage | 1 | - |
dc.citation.endPage | 7 | - |
dc.type.rims | ART | - |
dc.type.docType | Proceedings Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Operations Research & Management Science | - |
dc.relation.journalResearchArea | Mathematics | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Operations Research & Management Science | - |
dc.relation.journalWebOfScienceCategory | Mathematics, Applied | - |
dc.subject.keywordPlus | Computer vision | - |
dc.subject.keywordPlus | Deep neural networks | - |
dc.subject.keywordPlus | Curricula | - |
dc.subject.keywordPlus | Correction method | - |
dc.subject.keywordPlus | Curriculum learning | - |
dc.subject.keywordPlus | Labelings | - |
dc.subject.keywordPlus | Labour-intensive | - |
dc.subject.keywordPlus | Large amounts of data | - |
dc.subject.keywordPlus | Loss distribution | - |
dc.subject.keywordPlus | Neural-networks | - |
dc.subject.keywordPlus | Noisy labels | - |
dc.subject.keywordPlus | Performance | - |
dc.subject.keywordPlus | Self-supervision | - |
dc.subject.keywordAuthor | Curriculum Learning | - |
dc.subject.keywordAuthor | Noisy Label | - |
dc.subject.keywordAuthor | Self-Supervision | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9660078 | - |
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.