Dual branch guided contrastive learning for unsupervised pedestrian re-identification

The current unsupervised pedestrian re-identification algorithms using residual networks can only extract rough global features, but it can’t adequately reflect subtle local features. In addition, the pseudo labels generated by clustering methods introduce noise, which will affect the performance of...

Full description

Saved in:
Bibliographic Details
Main Authors: REN Hangjia, LIANG Fengmei
Format: Article
Language:zho
Published: Beijing Xintong Media Co., Ltd 2025-06-01
Series:Dianxin kexue
Subjects:
Online Access:http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2025125/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849472562361270272
author REN Hangjia
LIANG Fengmei
author_facet REN Hangjia
LIANG Fengmei
author_sort REN Hangjia
collection DOAJ
description The current unsupervised pedestrian re-identification algorithms using residual networks can only extract rough global features, but it can’t adequately reflect subtle local features. In addition, the pseudo labels generated by clustering methods introduce noise, which will affect the performance of feature discrimination. A dual branch guided contrastive learning method was proposed. Firstly, an effective feature extraction method was introduced, which divided the extracted features into global branches and local branches to improve the utilization of local information. Secondly, the consistency between global and local features was proposed to refine the pseudo labels for global feature prediction, utilizing the complementary relationship between local and global features, thereby effectively reducing the noise generated by pseudo label clustering. Finally, a contrastive learning module was proposed to perform contrastive learning on refined labels and improve the robustness of the model. The experimental results on the Market1501, DukeMTMC-ReID, and MSMT17 datasets validate the effectiveness of the proposed method.
format Article
id doaj-art-aeb8570cabcd4c45ac3dc450c45b4fa1
institution Kabale University
issn 1000-0801
language zho
publishDate 2025-06-01
publisher Beijing Xintong Media Co., Ltd
record_format Article
series Dianxin kexue
spelling doaj-art-aeb8570cabcd4c45ac3dc450c45b4fa12025-08-20T03:24:30ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012025-06-014192102112430246Dual branch guided contrastive learning for unsupervised pedestrian re-identificationREN HangjiaLIANG FengmeiThe current unsupervised pedestrian re-identification algorithms using residual networks can only extract rough global features, but it can’t adequately reflect subtle local features. In addition, the pseudo labels generated by clustering methods introduce noise, which will affect the performance of feature discrimination. A dual branch guided contrastive learning method was proposed. Firstly, an effective feature extraction method was introduced, which divided the extracted features into global branches and local branches to improve the utilization of local information. Secondly, the consistency between global and local features was proposed to refine the pseudo labels for global feature prediction, utilizing the complementary relationship between local and global features, thereby effectively reducing the noise generated by pseudo label clustering. Finally, a contrastive learning module was proposed to perform contrastive learning on refined labels and improve the robustness of the model. The experimental results on the Market1501, DukeMTMC-ReID, and MSMT17 datasets validate the effectiveness of the proposed method.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2025125/unsupervised pedestrian re-identificationglobal featurelocal featurelabel refinementcontrastive learning
spellingShingle REN Hangjia
LIANG Fengmei
Dual branch guided contrastive learning for unsupervised pedestrian re-identification
Dianxin kexue
unsupervised pedestrian re-identification
global feature
local feature
label refinement
contrastive learning
title Dual branch guided contrastive learning for unsupervised pedestrian re-identification
title_full Dual branch guided contrastive learning for unsupervised pedestrian re-identification
title_fullStr Dual branch guided contrastive learning for unsupervised pedestrian re-identification
title_full_unstemmed Dual branch guided contrastive learning for unsupervised pedestrian re-identification
title_short Dual branch guided contrastive learning for unsupervised pedestrian re-identification
title_sort dual branch guided contrastive learning for unsupervised pedestrian re identification
topic unsupervised pedestrian re-identification
global feature
local feature
label refinement
contrastive learning
url http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2025125/
work_keys_str_mv AT renhangjia dualbranchguidedcontrastivelearningforunsupervisedpedestrianreidentification
AT liangfengmei dualbranchguidedcontrastivelearningforunsupervisedpedestrianreidentification