Semi-Supervised Spatial Attention Method for Facial Attribute Editing
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yang, Hyeon Seok | - |
dc.contributor.author | Han, Jeong Hoon | - |
dc.contributor.author | Moon, Young Shik | - |
dc.date.accessioned | 2022-07-18T01:31:36Z | - |
dc.date.available | 2022-07-18T01:31:36Z | - |
dc.date.created | 2021-12-06 | - |
dc.date.issued | 2021-10 | - |
dc.identifier.issn | 1976-7277 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/108181 | - |
dc.description.abstract | In recent years, facial attribute editing has been successfully used to effectively change face images of various attributes based on generative adversarial networks and encoder-decoder models. However, existing models have a limitation in that they may change an unintended part in the process of changing an attribute or may generate an unnatural result. In this paper, we propose a model that improves the learning of the attention mask by adding a spatial attention mechanism based on the unified selective transfer network (referred to as STGAN) using semi-supervised learning. The proposed model can edit multiple attributes while preserving details independent of the attributes being edited. This study makes two main contributions to the literature. First, we propose an encoder-decoder model structure that learns and edits multiple facial attributes and suppresses distortion using an attention mask. Second, we define guide masks and propose a method and an objective function that use the guide masks for multiple facial attribute editing through semi-supervised learning. Through qualitative and quantitative evaluations of the experimental results, the proposed method was proven to yield improved results that preserve the image details by suppressing unintended changes than existing methods. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | 한국인터넷정보학회 | - |
dc.title | Semi-Supervised Spatial Attention Method for Facial Attribute Editing | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Moon, Young Shik | - |
dc.identifier.doi | 10.3837/tiis.2021.10.012 | - |
dc.identifier.scopusid | 2-s2.0-85119022848 | - |
dc.identifier.wosid | 000714446400012 | - |
dc.identifier.bibliographicCitation | KSII Transactions on Internet and Information Systems, v.15, no.10, pp.3685 - 3707 | - |
dc.relation.isPartOf | KSII Transactions on Internet and Information Systems | - |
dc.citation.title | KSII Transactions on Internet and Information Systems | - |
dc.citation.volume | 15 | - |
dc.citation.number | 10 | - |
dc.citation.startPage | 3685 | - |
dc.citation.endPage | 3707 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.identifier.kciid | ART002770885 | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.description.journalRegisteredClass | kci | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.subject.keywordAuthor | Facial attribute editing | - |
dc.subject.keywordAuthor | spatial attention mechanism | - |
dc.subject.keywordAuthor | semi-supervised learning | - |
dc.subject.keywordAuthor | generative adversarial network | - |
dc.subject.keywordAuthor | STGAN | - |
dc.identifier.url | https://kiss.kstudy.com/Detail/Ar?key=3909478 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
55 Hanyangdeahak-ro, Sangnok-gu, Ansan, Gyeonggi-do, 15588, Korea+82-31-400-4269 sweetbrain@hanyang.ac.kr
COPYRIGHT © 2021 HANYANG 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.