液晶与显示2024，Vol.39Issue(4)：506-521,16.DOI:10.37188/CJLCD.2023-0114
双注意力随机选择全局上下文细粒度识别网络
Dual-attention random selection global context fine-grained recognition network
摘要
Abstract
To address the difficulties of capturing the potential distinguishable features and subtle appearance differences in fine-grained image recognition tasks,dual-attention random selection global context fine-grained recognition network is proposed.Firstly,the ConvNeXt is taken as the backbone network,a dual-attention random selection module is proposed to perform channel random selection and spatial random selection on the features extracted at different stages,so that the network could focus on other potential subtle distinguishable features.Then,by using the global context attention module,the semantic information of top-level is applied to the middle-level to enhance the ability of the middle-level to locate potential subtle distinguishable features.Finally,the multi-branch loss is proposed,and classification loss is imposed on middle-level,top-level and concat-level characteristics.Combining the features extracted from different branches,the network is induced to obtain diverse distinguishable features.The network achieves the accuracies of 95.2%,92.1%,94.0%and 97.0%respectively on the three open datasets,Stanford-cars,CUB-200-2011,FGVC-Aircraft and dataset VMRURS in real scenes.The presented method in this paper greatly upgrades the comparison performance.关键词
细粒度识别/ConvNeXt/双注意力随机选择/全局上下文注意力/多分支损失Key words
fine-grained recognition/convnext/dual-attention random selection/global context attention/multi-branch loss分类
信息技术与安全科学引用本文复制引用
徐胜军,荆扬,段中兴,李明海,李海涛,刘福友..双注意力随机选择全局上下文细粒度识别网络[J].液晶与显示,2024,39(4):506-521,16.基金项目
国家自然科学基金(No.52278125) （No.52278125）
陕西省自然科学基础研究项目(No.2023-JC-YB-532,No.2022JQ-681) （No.2023-JC-YB-532,No.2022JQ-681）
陕西省重点研发计划(No.2021SF-429) （No.2021SF-429）
陕西省教育厅专项科研计划(No.20JK0721)Supported by National Natural Science Foundation of China(No.52278125) （No.20JK0721）
Natural Science Basic Research Program of Shaanxi(No.2023-JC-YB-532,No.2022JQ-681) （No.2023-JC-YB-532,No.2022JQ-681）
Key Research and Development Project of Shannxi Province(No.2021SF-429) （No.2021SF-429）
Special Scientific Research Project of Shannxi Provincial Education Department(No.20JK0721) （No.20JK0721）
