Observations on K-image Expansion of Image-Mixing Augmentation
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jeong, J. | - |
dc.contributor.author | Cha, S. | - |
dc.contributor.author | Choi, Jongwon | - |
dc.contributor.author | Yun, S. | - |
dc.contributor.author | Moon, T. | - |
dc.contributor.author | Yoo, Y. | - |
dc.date.accessioned | 2024-01-08T18:30:56Z | - |
dc.date.available | 2024-01-08T18:30:56Z | - |
dc.date.issued | 2023 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/69552 | - |
dc.description.abstract | Image-mixing augmentations (e.g., Mixup and CutMix), which typically involve mixing two images, have become the de-facto training techniques for image classification. Despite their huge success in image classification, the number of images to be mixed has not been elucidated in the literature: only the naive K-image expansion has been shown to lead to performance degradation. This study derives a new K-image mixing augmentation based on the stick-breaking process under Dirichlet prior distribution. We demonstrate superiority of our K-image expansion augmentation over conventional two-image mixing augmentation methods through extensive experiments and analyses: (1) more robust and generalized classifiers; (2) a more desirable loss landscape shape; (3) better adversarial robustness. Moreover, we show that our probabilistic model can measure the sample-wise uncertainty and boost the efficiency for network architecture search by achieving a 7-fold reduction in the search time. Author | - |
dc.format.extent | 1 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Observations on K-image Expansion of Image-Mixing Augmentation | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ACCESS.2023.3243108 | - |
dc.identifier.bibliographicCitation | IEEE Access, v.11, pp 1 - 1 | - |
dc.description.isOpenAccess | Y | - |
dc.identifier.wosid | 000944933200001 | - |
dc.identifier.scopusid | 2-s2.0-85148449165 | - |
dc.citation.endPage | 1 | - |
dc.citation.startPage | 1 | - |
dc.citation.title | IEEE Access | - |
dc.citation.volume | 11 | - |
dc.type.docType | Article | - |
dc.publisher.location | 미국 | - |
dc.subject.keywordAuthor | Augmentation | - |
dc.subject.keywordAuthor | Computer architecture | - |
dc.subject.keywordAuthor | Data augmentation | - |
dc.subject.keywordAuthor | Dirichlet process | - |
dc.subject.keywordAuthor | Image classification | - |
dc.subject.keywordAuthor | Image Classification | - |
dc.subject.keywordAuthor | Measurement uncertainty | - |
dc.subject.keywordAuthor | Probabilistic logic | - |
dc.subject.keywordAuthor | Robustness | - |
dc.subject.keywordAuthor | Uncertainty | - |
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.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang 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.