Fast Adaptation to Super-Resolution Networks via Meta-Learning
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Seobin | - |
dc.contributor.author | Yoo, Jinsu | - |
dc.contributor.author | Cho, Donghyeon | - |
dc.contributor.author | Kim, Jiwon | - |
dc.contributor.author | Kim, Tae Hyun | - |
dc.date.accessioned | 2022-07-07T17:24:32Z | - |
dc.date.available | 2022-07-07T17:24:32Z | - |
dc.date.created | 2021-05-14 | - |
dc.date.issued | 2020-08 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/145237 | - |
dc.description.abstract | Conventional supervised super-resolution (SR) approaches are trained with massive external SR datasets but fail to exploit desirable properties of the given test image. On the other hand, self-supervised SR approaches utilize the internal information within a test image but suffer from computational complexity in run-time. In this work, we observe the opportunity for further improvement of the performance of SISR without changing the architecture of conventional SR networks by practically exploiting additional information given from the input image. In the training stage, we train the network via meta-learning; thus, the network can quickly adapt to any input image at test time. Then, in the test stage, parameters of this meta-learned network are rapidly fine-tuned with only a few iterations by only using the given low-resolution image. The adaptation at the test time takes full advantage of patch-recurrence property observed in natural images. Our method effectively handles unknown SR kernels and can be applied to any existing model. We demonstrate that the proposed model-agnostic approach consistently improves the performance of conventional SR networks on various benchmark SR datasets. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Springer Nature Switzerland | - |
dc.title | Fast Adaptation to Super-Resolution Networks via Meta-Learning | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Tae Hyun | - |
dc.identifier.doi | 10.1007/978-3-030-58583-9_45 | - |
dc.identifier.bibliographicCitation | European Conference on Computer Vision, pp.754 - 769 | - |
dc.relation.isPartOf | European Conference on Computer Vision | - |
dc.citation.title | European Conference on Computer Vision | - |
dc.citation.startPage | 754 | - |
dc.citation.endPage | 769 | - |
dc.type.rims | ART | - |
dc.type.docType | Proceeding | - |
dc.description.journalClass | 3 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | other | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | Meta-learning | - |
dc.subject.keywordAuthor | Single-image-super-resolution | - |
dc.subject.keywordAuthor | Patch recurrence | - |
dc.identifier.url | https://link.springer.com/chapter/10.1007/978-3-030-58583-9_45 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
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.