Ajou University repository

Rethinking data augmentation for image super-resolution: A comprehensive analysis and a new strategyoa mark
Citations

SCOPUS

0

Citation Export

Publication Year
2020-01-01
Journal
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publisher
IEEE Computer Society
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.8372-8381
Mesh Keyword
Augmentation methodsComprehensive analysisCompression artifactsHigh resolution imageHigh-level visionsImage super resolutionsReal world environmentsSpatial relationships
All Science Classification Codes (ASJC)
SoftwareComputer Vision and Pattern Recognition
Abstract
Data augmentation is an effective way to improve the performance of deep networks. Unfortunately, current methods are mostly developed for high-level vision tasks (e.g., classification) and few are studied for low-level vision tasks (e.g., image restoration). In this paper, we provide a comprehensive analysis of the existing augmentation methods applied to the super-resolution task. We find that the methods discarding or manipulating the pixels or features too much hamper the image restoration, where the spatial relationship is very important. Based on our analyses, we propose CutBlur that cuts a low-resolution patch and pastes it to the corresponding high-resolution image region and vice versa. The key intuition of CutBlur is to enable a model to learn not only “how” but also “where” to super-resolve an image. By doing so, the model can understand “how much”, instead of blindly learning to apply super-resolution to every given pixel. Our method consistently and significantly improves the performance across various scenarios, especially when the model size is big and the data is collected under real-world environments. We also show that our method improves other low-level vision tasks, such as denoising and compression artifact removal.
ISSN
1063-6919
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36563
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85094324137&origin=inward
DOI
https://doi.org/10.1109/cvpr42600.2020.00840
Type
Conference
Funding
We would like to thank Clova AI Research team, especially Yunjey Choi, Seong Joon Oh, Youngjung Uh, Sangdoo Yun, Dongyoon Han, Youngjoon Yoo, and Jung-Woo Ha for their valuable comments and feedback. This work was supported by NAVER Corp and also by the National Research Foundation of Korea grant funded by the Korea government (MSIT) (no.NRF-2019R1A2C1006608)
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Sohn, Kyung-Ah Image
Sohn, Kyung-Ah손경아
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.