A Plug-in Method for Representation Factorization in Connectionist Models
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yoon, J.S. | - |
dc.contributor.author | Roh, M. | - |
dc.contributor.author | Suk, H. | - |
dc.date.accessioned | 2021-12-05T06:41:24Z | - |
dc.date.available | 2021-12-05T06:41:24Z | - |
dc.date.created | 2021-08-31 | - |
dc.date.issued | 2022-08 | - |
dc.identifier.issn | 2162-237X | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/129545 | - |
dc.description.abstract | In this article, we focus on decomposing latent representations in generative adversarial networks or learned feature representations in deep autoencoders into semantically controllable factors in a semisupervised manner, without modifying the original trained models. Particularly, we propose factors' decomposer-entangler network (FDEN) that learns to decompose a latent representation into mutually independent factors. Given a latent representation, the proposed framework draws a set of interpretable factors, each aligned to independent factors of variations by minimizing their total correlation in an information-theoretic means. As a plug-in method, we have applied our proposed FDEN to the existing networks of adversarially learned inference and pioneer network and performed computer vision tasks of image-to-image translation in semantic ways, e.g., changing styles, while keeping the identity of a subject, and object classification in a few-shot learning scheme. We have also validated the effectiveness of the proposed method with various ablation studies in the qualitative, quantitative, and statistical examination. IEEE | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.subject | Information theory | - |
dc.subject | Semantics | - |
dc.subject | Adversarial networks | - |
dc.subject | Connectionist models | - |
dc.subject | Feature representation | - |
dc.subject | Image translation | - |
dc.subject | Learning schemes | - |
dc.subject | Mutually independents | - |
dc.subject | Object classification | - |
dc.subject | Semi-supervised | - |
dc.subject | Learning systems | - |
dc.title | A Plug-in Method for Representation Factorization in Connectionist Models | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Suk, H. | - |
dc.identifier.doi | 10.1109/TNNLS.2021.3054480 | - |
dc.identifier.scopusid | 2-s2.0-85100869696 | - |
dc.identifier.wosid | 000732170900001 | - |
dc.identifier.bibliographicCitation | IEEE Transactions on Neural Networks and Learning Systems, v.33, no.8, pp.3792 - 3803 | - |
dc.relation.isPartOf | IEEE Transactions on Neural Networks and Learning Systems | - |
dc.citation.title | IEEE Transactions on Neural Networks and Learning Systems | - |
dc.citation.volume | 33 | - |
dc.citation.number | 8 | - |
dc.citation.startPage | 3792 | - |
dc.citation.endPage | 3803 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Hardware & Architecture | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Theory & Methods | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordPlus | Information theory | - |
dc.subject.keywordPlus | Semantics | - |
dc.subject.keywordPlus | Adversarial networks | - |
dc.subject.keywordPlus | Connectionist models | - |
dc.subject.keywordPlus | Feature representation | - |
dc.subject.keywordPlus | Image translation | - |
dc.subject.keywordPlus | Learning schemes | - |
dc.subject.keywordPlus | Mutually independents | - |
dc.subject.keywordPlus | Object classification | - |
dc.subject.keywordPlus | Semi-supervised | - |
dc.subject.keywordPlus | Learning systems | - |
dc.subject.keywordAuthor | Factorization | - |
dc.subject.keywordAuthor | few-shot learning | - |
dc.subject.keywordAuthor | image-to-image translation | - |
dc.subject.keywordAuthor | mutual information | - |
dc.subject.keywordAuthor | representation learning | - |
dc.subject.keywordAuthor | style transfer. | - |
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.