Regional Patch-Based Feature Interpolation Method for Effective Regularization
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jang, S. | - |
dc.contributor.author | Jin, K. | - |
dc.contributor.author | An, J. | - |
dc.contributor.author | Kim, Young Bin | - |
dc.date.available | 2020-04-17T03:20:33Z | - |
dc.date.issued | 2020-02 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/38574 | - |
dc.description.abstract | Deep Convolutional Neural Networks (CNNs) can be overly dependent on training data, causing a generalization problem in which trained models may not predict real-world datasets. To address this problem, various regularization methods such as image manipulation and feature map regularization have been proposed for their strong generalization ability. In this paper, we propose a regularization method that applies both image manipulation and feature map regularization based on patches. The method proposed in this paper has a regularization effect in two stages, which makes it possible to better generalize the model. Consequently, it improves the performance of the model. Moreover, our method adds features extracted from other images in the hidden state stage, which not only makes the model robust to noise but also captures the distribution of each label. Through experiments, we show that our method performs competently on models that generate a large number of parameter and multiple feature maps for the CIFAR and Tiny-ImageNet datasets. © 2013 IEEE. | - |
dc.format.extent | 8 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Regional Patch-Based Feature Interpolation Method for Effective Regularization | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ACCESS.2020.2974328 | - |
dc.identifier.bibliographicCitation | IEEE Access, v.8, pp 33658 - 33665 | - |
dc.description.isOpenAccess | Y | - |
dc.identifier.wosid | 000567604800049 | - |
dc.identifier.scopusid | 2-s2.0-85081182023 | - |
dc.citation.endPage | 33665 | - |
dc.citation.startPage | 33658 | - |
dc.citation.title | IEEE Access | - |
dc.citation.volume | 8 | - |
dc.type.docType | Article | - |
dc.publisher.location | 미국 | - |
dc.subject.keywordAuthor | computer vision | - |
dc.subject.keywordAuthor | Convolutional neural network | - |
dc.subject.keywordAuthor | manifold | - |
dc.subject.keywordAuthor | regularization | - |
dc.subject.keywordPlus | Computer vision | - |
dc.subject.keywordPlus | Convolution | - |
dc.subject.keywordPlus | Deep neural networks | - |
dc.subject.keywordPlus | Dynamic loads | - |
dc.subject.keywordPlus | Large dataset | - |
dc.subject.keywordPlus | Generalization ability | - |
dc.subject.keywordPlus | Image manipulation | - |
dc.subject.keywordPlus | Interpolation method | - |
dc.subject.keywordPlus | manifold | - |
dc.subject.keywordPlus | Multiple features | - |
dc.subject.keywordPlus | Real-world datasets | - |
dc.subject.keywordPlus | regularization | - |
dc.subject.keywordPlus | Regularization methods | - |
dc.subject.keywordPlus | Convolutional neural networks | - |
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.