Simple Yet Effective Way for Improving the Performance of Lossy Image Compression
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yeoe, Yoon-Jae | - |
dc.contributor.author | Shin, Yong-Goo | - |
dc.contributor.author | Sagong, Min-Cheol | - |
dc.contributor.author | Kim, Seung-Wook | - |
dc.contributor.author | Ko, Sung-Jea | - |
dc.date.accessioned | 2021-08-31T15:56:23Z | - |
dc.date.available | 2021-08-31T15:56:23Z | - |
dc.date.created | 2021-06-19 | - |
dc.date.issued | 2020 | - |
dc.identifier.issn | 1070-9908 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/58916 | - |
dc.description.abstract | Lossy image compression methods with deep neural network (DNN) include a quantization process between encoder and decoder networks as an essential part to increase the compression rate. However, the quantization operation impedes the flow of gradient and often disturbs the optimal learning of the encoder, which results in distortion in the reconstructed images. To alleviate this problem, this paper presents a simple yet effective way that enhances the performance of lossy image compression without imposing training overhead or modifying the original network architectures. In the proposed method, we utilize an auxiliary branch called a shortcut which directly connects the encoder and decoder. Since the shortcut does not include the quantization process, it supports the optimal learning of the encoder by flowing the accurate gradient. Furthermore, to assist the decoder which should handle additional feature maps obtained via the shortcut, we also propose a residual refinement unit (RRU) following the quantizer. The experimental results show that the image compression network trained with the proposed method remarkably improves the performance in terms of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and multi-scale structural similarity (MS-SSIM). | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | QUALITY ASSESSMENT | - |
dc.title | Simple Yet Effective Way for Improving the Performance of Lossy Image Compression | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Ko, Sung-Jea | - |
dc.identifier.doi | 10.1109/LSP.2020.2982561 | - |
dc.identifier.scopusid | 2-s2.0-85084282064 | - |
dc.identifier.wosid | 000531387400001 | - |
dc.identifier.bibliographicCitation | IEEE SIGNAL PROCESSING LETTERS, v.27, pp.530 - 534 | - |
dc.relation.isPartOf | IEEE SIGNAL PROCESSING LETTERS | - |
dc.citation.title | IEEE SIGNAL PROCESSING LETTERS | - |
dc.citation.volume | 27 | - |
dc.citation.startPage | 530 | - |
dc.citation.endPage | 534 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordPlus | QUALITY ASSESSMENT | - |
dc.subject.keywordAuthor | Convolutional neural network | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | image compression | - |
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.