计算机工程与应用2024，Vol.60Issue(19)：250-258,9.DOI:10.3778/j.issn.1002-8331.2307-0100
基于退化四元数注意力机制的轻量化Transformer去雨网络
Lightweight Transformer Deraining Network Based on Reduced Biquaternion Attention Mechanism
摘要
Abstract
The existing mainstream image deraining methods focus on improving the deraining performance but ignore the problem of excessive network computation overhead.A few lightweight network studies are restricted to changing the network's structure to reduce computation.The capability of the reduced biquaternion(RQ)to obtain more a priori infor-mation is used to propose a reduced biquaternion image deraining network as a solution to the above issue.The network's primary feature extraction module is the reduced biquaternion Swin-Transformer block(RQSTB).The RQSTB incorpo-rates the reduced biquaternion Transformer block,which utilizes the reduced biquaternion multi-headed attention mecha-nism to extract global feature information.Additionally,the reduced biquaternion multi-scale convolution module is inter-leaved to capture local multi-scale feature information.This combination compensates for the inherent lack of CNN's in-ductive biases that are absent in Transformer.It is experimentally demonstrated that this method achieves advanced levels of deraining performance,outperforming most existing image rain removal methods in terms of network parameters and computational complexity and demonstrating significant results in terms of both quantitative and qualitative metrics.关键词
图像去雨/退化四元数网络/Transformer/轻量化Key words
image deraining/reduced biquaternion network/Transformer/lightweight分类
信息技术与安全科学引用本文复制引用
熊贡鹤,陈飞龙,孙成立,郭桥生..基于退化四元数注意力机制的轻量化Transformer去雨网络[J].计算机工程与应用,2024,60(19):250-258,9.基金项目
国家自然科学基金(61861033) （61861033）
江西省教育厅科技项目(DA202104170) （DA202104170）
南昌航空大学博士启动基金(EA201904283) （EA201904283）
南昌航空大学研究生创新基金(YC2022-044). （YC2022-044）
