Improving Complex Scene Generation by Enhancing Multi-Scale Representations of GAN Discriminators
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, Hanbit | - |
dc.contributor.author | Lee, Sang-Goo | - |
dc.contributor.author | Park, Jaehui | - |
dc.contributor.author | Shim, Junho | - |
dc.date.accessioned | 2023-11-08T06:46:11Z | - |
dc.date.available | 2023-11-08T06:46:11Z | - |
dc.date.issued | 2023-04 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/151908 | - |
dc.description.abstract | While recent advances of GAN models enabled photo-realistic synthesis of various object images, challenges still remain in modeling more complex image distributions such as scenes with multiple objects. The difficulty lies in the high structural complexity of scene images, where the discriminator carries a heavy burden in discriminating complex structural differences between real and fake scene images. Therefore, enhancing the discriminative capability of the discriminator could be one of the effective strategies to improve the generation performance of GAN models. In this paper, we explore ways to boost the discriminative capability by leveraging two recent paradigms on visual representation learning: self-supervised learning and transfer learning. As the first approach, we propose a self-supervised auxiliary task tailored to enhance the multi-scale representations of the discriminator. In the second approach, we further enhance the discriminator by utilizing pretrained representations from various scene understanding models. To fully utilize knowledge from multiple expert models, we propose a multi-scale feature ensemble to mix multi-sale representations. Empirical results on challenging scene datasets demonstrate that the proposed strategies significantly advance the generation performance, enabling diverse and photo-realistic synthesis of complex scene images. | - |
dc.format.extent | 13 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Improving Complex Scene Generation by Enhancing Multi-Scale Representations of GAN Discriminators | - |
dc.type | Article | - |
dc.publisher.location | 미국 | - |
dc.identifier.doi | 10.1109/ACCESS.2023.3270561 | - |
dc.identifier.scopusid | 2-s2.0-85159688904 | - |
dc.identifier.wosid | 000988223900001 | - |
dc.identifier.bibliographicCitation | IEEE ACCESS, v.11, pp 43067 - 43079 | - |
dc.citation.title | IEEE ACCESS | - |
dc.citation.volume | 11 | - |
dc.citation.startPage | 43067 | - |
dc.citation.endPage | 43079 | - |
dc.type.docType | Article | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
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.subject.keywordAuthor | Image analysis | - |
dc.subject.keywordAuthor | Generative adversarial networks | - |
dc.subject.keywordAuthor | Transfer learning | - |
dc.subject.keywordAuthor | Feature extraction | - |
dc.subject.keywordAuthor | Self-supervised learning | - |
dc.subject.keywordAuthor | Generators | - |
dc.subject.keywordAuthor | scene generation | - |
dc.subject.keywordAuthor | self-supervised learning | - |
dc.subject.keywordAuthor | transfer learning | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/10109094 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
Sookmyung Women's University. Cheongpa-ro 47-gil 100 (Cheongpa-dong 2ga), Yongsan-gu, Seoul, 04310, Korea02-710-9127
Copyright©Sookmyung Women's 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.