基于局部实例匹配无监督式学习的行人重识别  

Unsupervised Learning Pedestrian Re-identification Based on Localized Instance Matching

作　　者：吴海丽 张月琴 庞俊奇 WU Haili;ZHANG Yueqin;PANG Junqi(Department of Computer Science and Technology,Taiyuan University,Taiyuan 030001,China;School of Information and Computer Science,Taiyuan University of Technology,Taiyuan 030002,China;College of Instruments and Electronics,North University of China,Taiyuan 030051,China)

机构地区：[1]太原学院计算机科学与技术系,太原030001 [2]太原理工大学信息与计算机学院,太原030002 [3]中北大学仪器与电子学院,太原030051

出　　处：《数据采集与处理》2023年第4期947-958,共12页Journal of Data Acquisition and Processing

基　　金：全国高等院校计算机基础教育研究会项目(2022-AFCEC-501);山西省教育科学规划课题(HLW-20127);山西省科技厅自然科学基金(20210302123057)。

摘　　要：无监督域适应(Unsupervised domain adaptation,UDA)方法通过全局特征分布匹配实现源域到目标域的知识迁移,但忽略了细粒度的局部实例信息。本文提出了一种基于双层域自适应(Two-tiered domain adaptation,TTDA)的无监督行人重识别方法,使用全尺寸网络(Omni-scale network,OSNet)作为骨干网络,在端到端深度学习框架中联合执行源域和目标域之间的全局特征分布匹配和局部实例匹配,从源域和目标域之间不同行人ID的关联中挖掘可迁移的有用知识,并通过知识选择机制提高了跨域适应性。在多个大型公开数据集上的实验结果表明,与其他先进方法相比,所提方法在源域到目标域的无监督行人重识别的平均精度均值(mean Average precision,mAP)和top-k命中率均取得显著提升。Unsupervised domain adaptation(UDA)methods leverage global feature distribution matching to realize knowledge transfer from source domain to target domain,while ignoring fine-grained local instance information.An unsupervised person re-identification method based on two-tiered domain adaptation(TTDA)is proposed,in which the omni-scale network(OSNet)is selected as the backbone network,and global feature distribution matching and localized instance matching between source and target domains are performed jointly in an end-to-end deep learning framework.And in order to effectively mine transferable useful knowledge from associations of different pedestrian IDs between source and target domains,the cross-domain adaptability is improved with a knowledge selection mechanism.Experimental results on multiple large-scale public datasets show that compared with other state-of-the-art methods,the proposed method achieves significant improvements in terms of mean average precision(mAP)and top-k hit rate for unsupervised cross-domain person re-identification tasks.

关 键 词：行人重识别 深度学习 无监督域 全局特征 局部实例匹配 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]