计算机应用研究2024，Vol.41Issue(4)：1228-1233,6.DOI:10.19734/j.issn.1001-3695.2023.07.0358
基于可靠性集成的无监督域自适应行人重识别
Unsupervised domain adaptive person re-identification based on reliability integration
摘要
Abstract
This paper proposed an unsupervised domain adaptation person re-identification base on reliability integration(UDA-RI)method aimed at alleviating the negative impact of noisy labels in the pseudo-labeling-based unsupervised domain adaptation person re-identification(UDA person ReID).This method consisted of two parts,such as progressive pseudo label refinement strategy and reliability integration strategy.The progressive pseudo label refinement strategy established a quantita-tive standard for measuring the uncertainty of pseudo labels and adopted gradual sampling to make the model more stable du-ring training.The reliability integration strategy considered knowledge from different adaptation moments,allocated weights ac-cording to the reliability levels of models from different iterations,integrated the self-integrated models with different architec-tures,and used them as the final inference model.Experimental results show that compared with the advanced unsupervised domain adaptation person re-identification methods,the UDA-RI method achieves superior performance on Market1501,Duke-MTMC-ReID,and MSMT17 datasets.关键词
无监督域自适应/行人重识别/可靠性/集成Key words
unsupervised domain adaptive/person re-identification/reliability/integration分类
信息技术与安全科学引用本文复制引用
文锐,孔广黔,段迅..基于可靠性集成的无监督域自适应行人重识别[J].计算机应用研究,2024,41(4):1228-1233,6.基金项目
国家自然科学基金资助项目(62266011) （62266011）
贵州省基础研究计划项目(黔科合基础-ZK[2022]一般119) （黔科合基础-ZK[2022]一般119）
