Kernel Attention Network for Single Image Super-Resolution

doi:10.1145/3398685

Kernel Attention Network for Single Image Super-Resolution

2020-07-05

24

PRE

AI

DOI：10.1145/3398685

Original request for help

Save

Abstract

En 中文

Recently, attention mechanisms have shown a developing tendency toward convolutional neural network (CNN), and some representative attention mechanisms, i.e., channel attention (CA) and spatial attention (SA) have been fully applied to single image super-resolution (SISR) tasks. However, the existing architectures directly apply these attention mechanisms to SISR without much consideration of the nature characteristic, resulting in less strong representational power. In this article, we propose a novel kernel attention module (KAM) for SISR, which enables the network to adjust its receptive field size corresponding to various scales of input by dynamically selecting the appropriate kernel. Based on this, we stack multiple kernel attention modules with group and residual connection to constitute a novel architecture for SISR, which enables our network to learn more distinguishing representations through filtering the information under different receptive fields. Thus, our network is more sensitive to multi-scale features, which enables our single network to deal with multi-scale SR task by predefining the upscaling modules. Besides, other attention mechanisms in super-resolution are also investigated and illustrated in detail in this article. Thanks to the kernel attention mechanism, the extensive benchmark evaluation shows that our method outperforms the other state-of-theart methods.

Keywords:

Image super-resolution

kernel attention

receptive field

multi-scale features

Kernel Attention Network for Single Image Super-Resolution

Abstract

AI Summary

Journal

Organization