Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 김태현 | - |
dc.date.accessioned | 2022-04-12T02:01:00Z | - |
dc.date.available | 2022-04-12T02:01:00Z | - |
dc.date.issued | 2020-08 | - |
dc.identifier.citation | Computer Vision – ECCV 2020, page. 754-769 | en_US |
dc.identifier.isbn | 978-3-030-58583-9 | - |
dc.identifier.uri | https://link.springer.com/chapter/10.1007/978-3-030-58583-9_45 | - |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/169916 | - |
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 single-image super-resolution (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. | en_US |
dc.description.sponsorship | This work was supported by the research fund of SK Telecom T-Brain, the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (NRF-2019R1A4A1029800), Samsung Research Funding Center of Samsung Electronics under Project Number SRFCIT1901-06, and Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No.2020-0-01373, Artificial Intelligence Graduate School Program(Hanyang University)). | en_US |
dc.language.iso | en | en_US |
dc.publisher | springer | en_US |
dc.subject | Deep learning | en_US |
dc.subject | Meta-learning | en_US |
dc.subject | Single-image super-resolution | en_US |
dc.subject | Patch recurrence | en_US |
dc.title | Fast Adaptation to Super-Resolution Networks via Meta-Learning | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.1007/978-3-030-58583-9_45 | - |
dc.relation.page | 1-17 | - |
dc.contributor.googleauthor | Park, Seobin | - |
dc.contributor.googleauthor | Yoo, Jinsu | - |
dc.contributor.googleauthor | Cho, Donghyeon | - |
dc.contributor.googleauthor | Kim, Jiwon | - |
dc.contributor.googleauthor | Kim, Tae Hyun | - |
dc.relation.code | 20200108 | - |
dc.sector.campus | S | - |
dc.sector.daehak | COLLEGE OF ENGINEERING[S] | - |
dc.sector.department | SCHOOL OF COMPUTER SCIENCE | - |
dc.identifier.pid | taehyunkim | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.