준지도학습을 이용한 노이즈 데이터 학습 방법
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 김지희 | - |
dc.contributor.author | 박상기 | - |
dc.contributor.author | 노시동 | - |
dc.contributor.author | 정기석 | - |
dc.date.accessioned | 2023-08-01T06:53:10Z | - |
dc.date.available | 2023-08-01T06:53:10Z | - |
dc.date.created | 2023-07-21 | - |
dc.date.issued | 2022-11 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/188560 | - |
dc.description.abstract | One of the major problems of modern neural networks is that models are vulnerable to data noise. In order to resolve this concern, research on removing noisy data has been actively conducted. However, there is a limitation that information in the removed noisy cannot be utilized for learning. In this paper, we propose an effective learning method based on FixMatch, one of the widely-used semi-supervised learning methods, and devise additional techniques that are effective for noisy labels such as model ensemble and parameter scheduling. Our experiments show that the proposed method achieves the best accuracy under every noise rate condition verifying that the proposed model is robust to data noise. | - |
dc.language | 한국어 | - |
dc.language.iso | ko | - |
dc.publisher | 대한임베디드공학회 | - |
dc.title | 준지도학습을 이용한 노이즈 데이터 학습 방법 | - |
dc.title.alternative | A Method of Learning Noisy Data using Semi-supervised Learning | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | 정기석 | - |
dc.identifier.bibliographicCitation | 2022 대한임베디드공학회 추계학술대회, v.0, no.0, pp.274 - 277 | - |
dc.relation.isPartOf | 2022 대한임베디드공학회 추계학술대회 | - |
dc.citation.title | 2022 대한임베디드공학회 추계학술대회 | - |
dc.citation.volume | 0 | - |
dc.citation.number | 0 | - |
dc.citation.startPage | 274 | - |
dc.citation.endPage | 277 | - |
dc.type.rims | ART | - |
dc.type.docType | Proceeding | - |
dc.description.journalClass | 3 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | other | - |
dc.subject.keywordAuthor | Noise | - |
dc.subject.keywordAuthor | Noisy data | - |
dc.subject.keywordAuthor | Cloud | - |
dc.subject.keywordAuthor | Semi-supervised learning | - |
dc.subject.keywordAuthor | EMA | - |
dc.identifier.url | http://esoc.hanyang.ac.kr/publications/2022/%EC%A4%80%EC%A7%80%EB%8F%84%ED%95%99%EC%8A%B5%EC%9D%84%20%EC%9D%B4%EC%9A%A9%ED%95%9C%20%EB%85%B8%EC%9D%B4%EC%A6%88%20%EB%8D%B0%EC%9D%B4%ED%84%B0%20%ED%95%99%EC%8A%B5%20%EB%B0%A9%EB%B2%95.pdf | - |
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.