EM-LAST: Effective Multidimensional Latent Space Transport for an Unpaired Image-to-Image Translation With an Energy-Based Model
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Han, Giwoong | - |
dc.contributor.author | Min, Jinhong | - |
dc.contributor.author | Han, Sung Won | - |
dc.date.accessioned | 2022-10-07T00:41:04Z | - |
dc.date.available | 2022-10-07T00:41:04Z | - |
dc.date.created | 2022-10-06 | - |
dc.date.issued | 2022 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/144179 | - |
dc.description.abstract | For an unpaired image-to-image translation to work effectively, the latent space of each image domain must be well-designed. The codes of each style must be translated toward the target while preserving the parts corresponding to the source content. In general, most Variational Autoencoder (VAE)-based models use a one-dimensional latent space. However, to apply high dimensional methodologies such as vector quantization, controlling a multidimensional latent space is necessary. In this study, among the VAE-based models that use relatively complex multidimensional latent spaces, we apply an Energy-Based Model and Vector-Quantized VAE v2, with the latter as the main model. We show that among the latent spaces that represent each image domain, the importance of each feature at the top and bottom latent spaces must be interpreted differently for appropriate translation. Therefore, we argue that simply understanding the features of latent space composition well can show effective image translation results. We also present various analyses and visual outcomes of multidimensional latent space transport. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | EM-LAST: Effective Multidimensional Latent Space Transport for an Unpaired Image-to-Image Translation With an Energy-Based Model | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Han, Sung Won | - |
dc.identifier.doi | 10.1109/ACCESS.2022.3189352 | - |
dc.identifier.scopusid | 2-s2.0-85134256402 | - |
dc.identifier.wosid | 000838494400001 | - |
dc.identifier.bibliographicCitation | IEEE ACCESS, v.10, pp.72839 - 72849 | - |
dc.relation.isPartOf | IEEE ACCESS | - |
dc.citation.title | IEEE ACCESS | - |
dc.citation.volume | 10 | - |
dc.citation.startPage | 72839 | - |
dc.citation.endPage | 72849 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
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 | Aerospace electronics | - |
dc.subject.keywordAuthor | Decoding | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | Energy-based model | - |
dc.subject.keywordAuthor | Generative adversarial networks | - |
dc.subject.keywordAuthor | Langevin dynamics | - |
dc.subject.keywordAuthor | Licenses | - |
dc.subject.keywordAuthor | Task analysis | - |
dc.subject.keywordAuthor | Visualization | - |
dc.subject.keywordAuthor | image-to-image translation | - |
dc.subject.keywordAuthor | multidimensional latent space | - |
dc.subject.keywordAuthor | vector-quantized variational autoencoder | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
145 Anam-ro, Seongbuk-gu, Seoul, 02841, Korea+82-2-3290-2963
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.