Skip to main navigation Skip to search Skip to main content

HAAT: Hybrid Attention Aggregation Transformer for Image Super-Resolution

  • Song Jiang Lai
  • , Tsun Hin Cheung
  • , Ka Chun Fung
  • , Kai Wen Xue
  • , Kin Man Lam

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

In the research area of image super-resolution, Swin-transformer-based models are favored for their global spatial modeling and shifting window attention mechanism.However, existing methods often limit self-attention to non-overlapping windows to cut costs and ignore the useful information that exists across channels.To address this issue, this paper introduces a novel model, the Hybrid Attention Aggregation Transformer (HAAT), designed to better leverage feature information.HAAT is constructed by integrating Swin-Dense-Residual-Connected Blocks (SDRCB) with Hybrid Grid Attention Blocks (HGAB).SDRCB expands the receptive field while maintaining a streamlined architecture, resulting in enhanced performance.HGAB incorporates channel attention, sparse attention, and window attention to improve nonlocal feature fusion and achieve more visually compelling results.Experimental evaluations demonstrate that HAAT surpasses state-of-the-art methods on benchmark datasets.

Original languageEnglish
Title of host publicationInternational Workshop on Advanced Imaging Technology, IWAIT 2025
EditorsMasayuki Nakajima, Chuan-Yu Chang, Chia-Hung Yeh, Jae-Gon Kim, Kemao Qian, Phooi Yee Lau
PublisherSPIE
Pages1-6
Number of pages6
ISBN (Electronic)9781510688124
DOIs
Publication statusPublished - Feb 2025
Event2025 International Workshop on Advanced Imaging Technology, IWAIT 2025 - Douliu City, Taiwan
Duration: 6 Jan 2025 → 8 Jan 2025

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume13510
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference2025 International Workshop on Advanced Imaging Technology, IWAIT 2025
Country/TerritoryTaiwan
CityDouliu City
Period6/01/25 → 8/01/25

Keywords

  • Attention mechanism
  • Computer vision
  • Image super-resolution
  • Transformer

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'HAAT: Hybrid Attention Aggregation Transformer for Image Super-Resolution'. Together they form a unique fingerprint.

Cite this