# GRAN: Ghost Residual Attention Network for Single Image Super Resolution

## TL;DR

GRAN is an efficient super-resolution network that reduces computational resources by using Ghost Modules and attention mechanisms, achieving high performance with significantly fewer parameters and FLOPs.

## Contribution

The paper introduces Ghost Residual Attention Blocks combining Ghost Modules and attention to improve efficiency in super-resolution networks.

## Key findings

- Achieves higher super-resolution performance with over ten times fewer parameters and FLOPs.
- Reduces redundant features, saving memory and computation.
- Demonstrates superior qualitative and quantitative results on benchmark datasets.

## Abstract

Recently, many works have designed wider and deeper networks to achieve higher image super-resolution performance. Despite their outstanding performance, they still suffer from high computational resources, preventing them from directly applying to embedded devices. To reduce the computation resources and maintain performance, we propose a novel Ghost Residual Attention Network (GRAN) for efficient super-resolution. This paper introduces Ghost Residual Attention Block (GRAB) groups to overcome the drawbacks of the standard convolutional operation, i.e., redundancy of the intermediate feature. GRAB consists of the Ghost Module and Channel and Spatial Attention Module (CSAM) to alleviate the generation of redundant features. Specifically, Ghost Module can reveal information underlying intrinsic features by employing linear operations to replace the standard convolutions. Reducing redundant features by the Ghost Module, our model decreases memory and computing resource requirements in the network. The CSAM pays more comprehensive attention to where and what the feature extraction is, which is critical to recovering the image details. Experiments conducted on the benchmark datasets demonstrate the superior performance of our method in both qualitative and quantitative. Compared to the baseline models, we achieve higher performance with lower computational resources, whose parameters and FLOPs have decreased by more than ten times.