Single Image Super-Resolution via a Holistic Attention Network

08/20/2020 ∙ by Ben Niu, et al. ∙ 0

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.



There are no comments yet.


page 8

page 11

page 12

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.