Single Image Super-Resolution via a Holistic Attention Network

Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in each layer. However, channel attention treats each convolution layer as a separate process that misses the correlati...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-08
Main Authors: Niu, Ben, Wen, Weilei, Ren, Wenqi, Zhang, Xiangde, Yang, Lianping, Wang, Shuzhen, Zhang, Kaihao, Cao, Xiaochun, Shen, Haifeng
Format: Article
Language:English
Subjects:
Confidence
Convolution
Image resolution
Modules
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in each layer. However, channel attention treats each convolution layer as a separate process that misses the correlation among different layers. To address this problem, we propose a new holistic attention network (HAN), which consists of a layer attention module (LAM) and a channel-spatial attention module (CSAM), to model the holistic interdependencies among layers, channels, and positions. Specifically, the proposed LAM adaptively emphasizes hierarchical features by considering correlations among layers. Meanwhile, CSAM learns the confidence at all the positions of each channel to selectively capture more informative features. Extensive experiments demonstrate that the proposed HAN performs favorably against the state-of-the-art single image super-resolution approaches.
ISSN:2331-8422