Pseudo Label Purification with Dual Contrastive Learning for Unsupervised Vehicle Re-Identification  

作　　者：Jiyang Xu Qi Wang Xin Xiong Weidong Min Jiang Luo Di Gai Qing Han 

机构地区：[1]School of Mathematics and Computer Sciences,Nanchang University,Nanchang,330031,China [2]The First Affiliated Hospital,Jiangxi Medical College,Nanchang University,Nanchang,330006,China [3]Institute of Metaverse,Nanchang University,Nanchang,330031,China [4]Jiangxi Fangxing Technology Company Limited,Nanchang,330025,China

出　　处：《Computers, Materials & Continua》2025年第3期3921-3941,共21页计算机、材料和连续体(英文)

基　　金：supported by the National Natural Science Foundation of China under Grant Nos.62461037,62076117 and 62166026;the Jiangxi Provincial Natural Science Foundation under Grant Nos.20224BAB212011,20232BAB202051,20232BAB212008 and 20242BAB25078;the Jiangxi Provincial Key Laboratory of Virtual Reality under Grant No.2024SSY03151.

摘　　要：The unsupervised vehicle re-identification task aims at identifying specific vehicles in surveillance videos without utilizing annotation information.Due to the higher similarity in appearance between vehicles compared to pedestrians,pseudo-labels generated through clustering are ineffective in mitigating the impact of noise,and the feature distance between inter-class and intra-class has not been adequately improved.To address the aforementioned issues,we design a dual contrastive learning method based on knowledge distillation.During each iteration,we utilize a teacher model to randomly partition the entire dataset into two sub-domains based on clustering pseudo-label categories.By conducting contrastive learning between the two student models,we extract more discernible vehicle identity cues to improve the problem of imbalanced data distribution.Subsequently,we propose a context-aware pseudo label refinement strategy that leverages contextual features by progressively associating granularity information from different bottleneck blocks.To produce more trustworthy pseudo-labels and lessen noise interference during the clustering process,the context-aware scores are obtained by calculating the similarity between global features and contextual ones,which are subsequently added to the pseudo-label encoding process.The proposed method has achieved excellent performance in overcoming label noise and optimizing data distribution through extensive experimental results on publicly available datasets.

关 键 词：Unsupervised vehicle re-identification dual contrastive learning pseudo label refinement knowledge distillation 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]