Fine-grained neural architecture search for image super-resolution
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Heewon | - |
dc.contributor.author | Hong, Seokil | - |
dc.contributor.author | Han, Bohyung | - |
dc.contributor.author | Myeong, Heesoo | - |
dc.contributor.author | Lee, Kyoung Mu | - |
dc.date.accessioned | 2023-03-22T03:40:03Z | - |
dc.date.available | 2023-03-22T03:40:03Z | - |
dc.date.created | 2023-03-22 | - |
dc.date.issued | 2022-11 | - |
dc.identifier.issn | 1047-3203 | - |
dc.identifier.uri | http://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/43434 | - |
dc.description.abstract | Designing efficient deep neural networks has achieved great interest in image super-resolution (SR). However, exploring diverse network structures is computationally expensive. More importantly, each layer in a network has a distinct role that leads to the design of a specialized structure. In this work, we present a novel neural architecture search (NAS) algorithm that efficiently explores layer-wise structures. Specifically, we construct a supernet allowing flexibility in choosing the number of channels and per-channel activation functions according to the role of each layer. The search process runs efficiently via channel pruning since gradient descent jointly optimizes the Mult-Adds and the accuracy of the searched models. We facilitate estimating the model Mult-Adds in a differentiable manner using relaxations in the backward pass. The searched model, named FGNAS, outperforms the state-of-the-art NAS-based SR methods by a large margin. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | ACADEMIC PRESS INC ELSEVIER SCIENCE | - |
dc.relation.isPartOf | JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION | - |
dc.title | Fine-grained neural architecture search for image super-resolution | - |
dc.type | Article | - |
dc.identifier.doi | 10.1016/j.jvcir.2022.103654 | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, v.89 | - |
dc.description.journalClass | 1 | - |
dc.identifier.wosid | 000873807300009 | - |
dc.identifier.scopusid | 2-s2.0-85139592143 | - |
dc.citation.title | JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION | - |
dc.citation.volume | 89 | - |
dc.contributor.affiliatedAuthor | Kim, Heewon | - |
dc.identifier.url | https://www.sciencedirect.com/science/article/pii/S1047320322001742?via%3Dihub | - |
dc.type.docType | Article | - |
dc.description.isOpenAccess | N | - |
dc.subject.keywordAuthor | Image super-resolution | - |
dc.subject.keywordAuthor | Neural architecture search | - |
dc.subject.keywordAuthor | Convolutional neural network | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Software Engineering | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
Soongsil University Library 369 Sangdo-Ro, Dongjak-Gu, Seoul, Korea (06978)02-820-0733
COPYRIGHT ⓒ SOONGSIL 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.