A Lightweight Multi-Scale Based Attention Network for Image Super-Resolution

Yanjie YANG, Jun LUO, Huayan PU, Mingliang ZHOU, Xuekai WEI, Taiping ZHANG, Zhaowei SHANG

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

Abstract

In this paper, we propose a lightweight multi-scale based attention network (MBAN) for single-image super-resolution (SISR). First, a deep feature transform block (DFTB) is designed for multi-scale feature extraction; this block combines group convolution and improved channel attention (ICA) for performance purposes while remaining sufficiently lightweight. Second, a dual multi-scale attention block (DMAB) is proposed for long-range information interaction; this block employs different window sizes for self-attention (SA) and short connections between different branches to achieve multiscale attention interaction. Finally, our MBAN is constructed by cascaded multi-scale based attention blocks (MBABs) that perform detail restoration; these blocks simultaneously extract multi-scale local features and integrate multi-scale global features with the DFTBs and DMABs. Extensive experiments suggest the superiority of our MBAN over the state-of-the-art (SOTA) lightweight SR methods in terms of both quantitative metrics and visual quality.

Original languageEnglish
Title of host publicationIECON 2023 : 49th Annual Conference of the IEEE Industrial Electronics Society
PublisherIEEE Computer Society
Number of pages6
ISBN (Electronic)9798350331820
DOIs
Publication statusPublished - 2023
Externally publishedYes
Event49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023 - Singapore, Singapore
Duration: 16 Oct 202319 Oct 2023

Publication series

NameIECON Proceedings (Industrial Electronics Conference)
ISSN (Print)2162-4704
ISSN (Electronic)2577-1647

Conference

Conference49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023
Country/TerritorySingapore
CitySingapore
Period16/10/2319/10/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

  • attention
  • lightweight
  • multi-scale
  • super-resolution

Fingerprint

Dive into the research topics of 'A Lightweight Multi-Scale Based Attention Network for Image Super-Resolution'. Together they form a unique fingerprint.

Cite this