Deep Interleaved Network for Single Image Super-Resolution with Asymmetric Co-Attention
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence. Main track. Pages 537-543.
https://doi.org/10.24963/ijcai.2020/75
Keywords
- Computer Vision: 2D and 3D Computer Vision
Abstract
Recently, Convolutional Neural Networks (CNN) based image super-resolution (SR) have shown significant success in the literature. However, these methods are implemented as single-path stream to enrich feature maps from the input for the final prediction, which fail to fully incorporate former low-level features into later high-level features. In this paper, to tackle this problem, we propose a deep interleaved network (DIN) to learn how information at different states should be combined for image SR where shallow information guides deep representative features prediction. Our DIN follows a multi-branch pattern allowing multiple interconnected branches to interleave and fuse at different states. Besides, the asymmetric co-attention (AsyCA) is proposed and attacked to the interleaved nodes to adaptively emphasize informative features from different states and improve the discriminative ability of networks. Extensive experiments demonstrate the superiority of our proposed DIN in comparison with the state-of-the-art SR methods.
Full text extracted automatically from the PDF; figures, tables and equations may differ. The PDF is the version of record.
@inproceedings{ijcai2020p75,
title = {Deep Interleaved Network for Single Image Super-Resolution with Asymmetric Co-Attention},
author = {Li, Feng and Cong, Runmin and Bai, Huihui and He, Yifan},
booktitle = {Proceedings of the Twenty-Ninth International Joint Conference on
Artificial Intelligence, {IJCAI-20}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Christian Bessiere},
pages = {537--543},
year = {2020},
month = {7},
note = {Main track},
doi = {10.24963/ijcai.2020/75},
url = {https://doi.org/10.24963/ijcai.2020/75},
}
TY - CPAPER TI - Deep Interleaved Network for Single Image Super-Resolution with Asymmetric Co-Attention AU - Li, Feng AU - Cong, Runmin AU - Bai, Huihui AU - He, Yifan T2 - Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20 PB - International Joint Conferences on Artificial Intelligence Organization PY - 2020 SP - 537 EP - 543 DO - 10.24963/ijcai.2020/75 UR - https://doi.org/10.24963/ijcai.2020/75 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
