@inproceedings{92da91ec059f431aa4b531262b8f95dd,
title = "HAAT: Hybrid Attention Aggregation Transformer for Image Super-Resolution",
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.",
keywords = "Attention mechanism, Computer vision, Image super-resolution, Transformer",
author = "Lai, \{Song Jiang\} and Cheung, \{Tsun Hin\} and Fung, \{Ka Chun\} and Xue, \{Kai Wen\} and Lam, \{Kin Man\}",
note = "Publisher Copyright: {\textcopyright} 2024 SPIE.; 2025 International Workshop on Advanced Imaging Technology, IWAIT 2025 ; Conference date: 06-01-2025 Through 08-01-2025",
year = "2025",
month = feb,
doi = "10.1117/12.3058003",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
pages = "1--6",
editor = "Masayuki Nakajima and Chuan-Yu Chang and Chia-Hung Yeh and Jae-Gon Kim and Kemao Qian and Lau, \{Phooi Yee\}",
booktitle = "International Workshop on Advanced Imaging Technology, IWAIT 2025",
address = "United States",
}