PMD-Transformer: A Domain Generalization Approach for Person Re-Identification

Domain generalization person re-identification (DG-ReID) aims to address the performance degradation caused by domain shift between the training domain and unseen target domains. Transformers often demonstrate better generalization ability than CNNs due to their self-attention mechanism and capacity...

Full description

Saved in:
Bibliographic Details
Main Authors: Xingguo Jiang, Ling Yu, Guojun Lin, Yuchao Zhang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11015796/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850230645875277824
author Xingguo Jiang
Ling Yu
Guojun Lin
Yuchao Zhang
author_facet Xingguo Jiang
Ling Yu
Guojun Lin
Yuchao Zhang
author_sort Xingguo Jiang
collection DOAJ
description Domain generalization person re-identification (DG-ReID) aims to address the performance degradation caused by domain shift between the training domain and unseen target domains. Transformers often demonstrate better generalization ability than CNNs due to their self-attention mechanism and capacity for capturing global features. However, the supervised learning strategy on the source domain makes the Transformer-based ReID model inevitably overfit the bias in some regions. Therefore, a transformer model (PMD Transformer) for DG-ReID is proposed. First, by introducing relative position coding, it prevents the person image block from losing its relative position information when passing through the attention mechanism and improves the extraction of person features. Second, in order to solve the excessive attention of the model to the features of some regions and thus the overfitting phenomenon, the part mask attention (PMA) module is designed to limit the scope of the attention mechanism and improve the computational efficiency. Finally, a new feedforward network (DRFNN) is used to enhance the mastery of spatial information and further improve the generalization performance of the model. The experimental results show that, in the setting where Market is the source domain and Duke is the target domain, the average precision (mAP) and Rank-1 metrics increased by 12.5% and 9.2%, respectively, compared to the optimal algorithm. In the setting where Duke is the source domain and CUHK03-NP is the target domain, the mAP and Rank-1 metrics increased by 10.5% and 8.6%, respectively. The experiments demonstrate that the proposed model exhibits outstanding generalization ability in DG-ReID.
format Article
id doaj-art-b1bc0cf1084942978072dc57bc6f4a4a
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-b1bc0cf1084942978072dc57bc6f4a4a2025-08-20T02:03:47ZengIEEEIEEE Access2169-35362025-01-0113931789318910.1109/ACCESS.2025.357392111015796PMD-Transformer: A Domain Generalization Approach for Person Re-IdentificationXingguo Jiang0https://orcid.org/0009-0006-9623-8479Ling Yu1https://orcid.org/0009-0002-6317-2275Guojun Lin2https://orcid.org/0000-0002-8707-5720Yuchao Zhang3https://orcid.org/0009-0008-8845-3093School of Automation and Information Engineering, Sichuan University of Science and Engineering, Yibin, ChinaSchool of Automation and Information Engineering, Sichuan University of Science and Engineering, Yibin, ChinaSchool of Automation and Information Engineering, Sichuan University of Science and Engineering, Yibin, ChinaSchool of Automation and Information Engineering, Sichuan University of Science and Engineering, Yibin, ChinaDomain generalization person re-identification (DG-ReID) aims to address the performance degradation caused by domain shift between the training domain and unseen target domains. Transformers often demonstrate better generalization ability than CNNs due to their self-attention mechanism and capacity for capturing global features. However, the supervised learning strategy on the source domain makes the Transformer-based ReID model inevitably overfit the bias in some regions. Therefore, a transformer model (PMD Transformer) for DG-ReID is proposed. First, by introducing relative position coding, it prevents the person image block from losing its relative position information when passing through the attention mechanism and improves the extraction of person features. Second, in order to solve the excessive attention of the model to the features of some regions and thus the overfitting phenomenon, the part mask attention (PMA) module is designed to limit the scope of the attention mechanism and improve the computational efficiency. Finally, a new feedforward network (DRFNN) is used to enhance the mastery of spatial information and further improve the generalization performance of the model. The experimental results show that, in the setting where Market is the source domain and Duke is the target domain, the average precision (mAP) and Rank-1 metrics increased by 12.5% and 9.2%, respectively, compared to the optimal algorithm. In the setting where Duke is the source domain and CUHK03-NP is the target domain, the mAP and Rank-1 metrics increased by 10.5% and 8.6%, respectively. The experiments demonstrate that the proposed model exhibits outstanding generalization ability in DG-ReID.https://ieeexplore.ieee.org/document/11015796/Person re-identificationdomain generalizationtransformerrelative positional encoding
spellingShingle Xingguo Jiang
Ling Yu
Guojun Lin
Yuchao Zhang
PMD-Transformer: A Domain Generalization Approach for Person Re-Identification
IEEE Access
Person re-identification
domain generalization
transformer
relative positional encoding
title PMD-Transformer: A Domain Generalization Approach for Person Re-Identification
title_full PMD-Transformer: A Domain Generalization Approach for Person Re-Identification
title_fullStr PMD-Transformer: A Domain Generalization Approach for Person Re-Identification
title_full_unstemmed PMD-Transformer: A Domain Generalization Approach for Person Re-Identification
title_short PMD-Transformer: A Domain Generalization Approach for Person Re-Identification
title_sort pmd transformer a domain generalization approach for person re identification
topic Person re-identification
domain generalization
transformer
relative positional encoding
url https://ieeexplore.ieee.org/document/11015796/
work_keys_str_mv AT xingguojiang pmdtransformeradomaingeneralizationapproachforpersonreidentification
AT lingyu pmdtransformeradomaingeneralizationapproachforpersonreidentification
AT guojunlin pmdtransformeradomaingeneralizationapproachforpersonreidentification
AT yuchaozhang pmdtransformeradomaingeneralizationapproachforpersonreidentification