English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recently, many works have designed wider and deeper networks to achievehigher image super-resolution performance. Despite their outstandingperformance, they still suffer from high computational resources, preventingthem from directly applying to embedded devices. To reduce the computationresources and maintain performance, we propose a novel Ghost Residual AttentionNetwork (GRAN) for efficient super-resolution. This paper introduces GhostResidual Attention Block (GRAB) groups to overcome the drawbacks of thestandard 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, GhostModule can reveal information underlying intrinsic features by employing linearoperations to replace the standard convolutions. Reducing redundant features bythe Ghost Module, our model decreases memory and computing resourcerequirements in the network. The CSAM pays more comprehensive attention towhere and what the feature extraction is, which is critical to recovering theimage details. Experiments conducted on the benchmark datasets demonstrate thesuperior performance of our method in both qualitative and quantitative.Compared to the baseline models, we achieve higher performance with lowercomputational resources, whose parameters and FLOPs have decreased by more thanten times.

GRAN: Ghost Residual Attention Network for Single Image Super Resolution