计算机工程2025，Vol.51Issue(11)：304-316,13.DOI:10.19678/j.issn.1000-3428.0069486
融合注意力机制的师生网络无监督行人重识别
Unsupervised Person Re-Identification for Teacher-Student Networks Incorporating Attention Mechanism
摘要
Abstract
Unsupervised Domain Adaptation(UDA)person Re-Identification(Re-ID)aims to transfer labeled source domain knowledge to an unlabeled target domain,which is very challenging owing to existing problems such as pseudo-label noise and domain gaps.Therefore,a Heterogeneous Teacher-Student network with Attention mechanisms(HTSA)is proposed to effectively reduce the influence of pseudo-label noise and focus on the key information of pedestrians while filtering out irrelevant background information.This study adopts Domain-Specific Batch Normalization(DSBN)to attenuate the performance degradation caused by domain gaps.Additionally,a novel data augmentation method is adopted to independently process two equally sized parts of the input image after width splitting,thereby enhancing the generalization ability.The experimental results reveal that mean Average Precision(mAP)and Rank-1 on DukeMTMC-reID→MSMT17 reach 40.3％and 71.0％,respectively,whereas those on Market-1501→MSMT17 reach 37.7％and 67.7％,respectively.This result demonstrates the effectiveness of the proposed method.关键词
行人重识别/无监督域自适应/伪标签噪声/注意力机制/师生网络Key words
person Re-Identification(Re-ID)/Unsupervised Domain Adaptation(UDA)/pseudo-label noise/attention mechanism/teacher-student network分类
计算机与自动化引用本文复制引用
陈玉敏,车进,吴金蔓..融合注意力机制的师生网络无监督行人重识别[J].计算机工程,2025,51(11):304-316,13.基金项目
国家自然科学基金(62366042). （62366042）
