Contrastive learning enhanced pseudo-labeling for unsupervised domain adaptation in person re-identification.
Person re-identification (ReID) technology has many applications in intelligent surveillance and public safety. However, the domain difference between the source and target domains makes the generalization ability of the model extremely challenging. To reduce the dependence on labeled data, Unsuperv...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0328131 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839625102837153792 |
|---|---|
| author | Xuemei Bai Yuqing Zhang Chenjie Zhang Zhijun Wang |
| author_facet | Xuemei Bai Yuqing Zhang Chenjie Zhang Zhijun Wang |
| author_sort | Xuemei Bai |
| collection | DOAJ |
| description | Person re-identification (ReID) technology has many applications in intelligent surveillance and public safety. However, the domain difference between the source and target domains makes the generalization ability of the model extremely challenging. To reduce the dependence on labeled data, Unsupervised Domain Adaptation (UDA) methods have become an effective way to solve this problem. However, the influence of pseudo-label generated noise on model training in existing UDA methods is still significant, resulting in limited model performance on the target domain. For this reason, this paper proposes a contrast learning-based pseudo-label refinement with probabilistic uncertainty in the unsupervised domain, adapted to Person re-identification, aiming to improve the effectiveness of the unsupervised domain adapted to Person re-identification. We first enhance the feature representation of the target domain samples based on the contrast learning technique to improve their discrimination in the feature space, thereby enhancing the cross-domain migration performance of the model. Subsequently, an innovative loss function is proposed to effectively reduce the interference of label noise on the training process by refining the generation process of pseudo-labels, which solves the negative impact of inaccurate pseudo-labels on model training. Through a series of experimental validation, the method experiments on two large-scale public datasets, Market1501 and DukeMTMC, and the Rank-1 accuracy of the proposed method reaches 91.4% and 81.4%, with the mean average precision (mAP) of 79.0% and 67.9%, respectively, which proves that the research in this paper provides a good solution for the Person re-identification task with effective technical support for label noise processing and model generalization capability improvement. |
| format | Article |
| id | doaj-art-40f35d6a387e452b98ece91f6dfb12c6 |
| institution | Matheson Library |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-40f35d6a387e452b98ece91f6dfb12c62025-07-18T05:31:06ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01207e032813110.1371/journal.pone.0328131Contrastive learning enhanced pseudo-labeling for unsupervised domain adaptation in person re-identification.Xuemei BaiYuqing ZhangChenjie ZhangZhijun WangPerson re-identification (ReID) technology has many applications in intelligent surveillance and public safety. However, the domain difference between the source and target domains makes the generalization ability of the model extremely challenging. To reduce the dependence on labeled data, Unsupervised Domain Adaptation (UDA) methods have become an effective way to solve this problem. However, the influence of pseudo-label generated noise on model training in existing UDA methods is still significant, resulting in limited model performance on the target domain. For this reason, this paper proposes a contrast learning-based pseudo-label refinement with probabilistic uncertainty in the unsupervised domain, adapted to Person re-identification, aiming to improve the effectiveness of the unsupervised domain adapted to Person re-identification. We first enhance the feature representation of the target domain samples based on the contrast learning technique to improve their discrimination in the feature space, thereby enhancing the cross-domain migration performance of the model. Subsequently, an innovative loss function is proposed to effectively reduce the interference of label noise on the training process by refining the generation process of pseudo-labels, which solves the negative impact of inaccurate pseudo-labels on model training. Through a series of experimental validation, the method experiments on two large-scale public datasets, Market1501 and DukeMTMC, and the Rank-1 accuracy of the proposed method reaches 91.4% and 81.4%, with the mean average precision (mAP) of 79.0% and 67.9%, respectively, which proves that the research in this paper provides a good solution for the Person re-identification task with effective technical support for label noise processing and model generalization capability improvement.https://doi.org/10.1371/journal.pone.0328131 |
| spellingShingle | Xuemei Bai Yuqing Zhang Chenjie Zhang Zhijun Wang Contrastive learning enhanced pseudo-labeling for unsupervised domain adaptation in person re-identification. PLoS ONE |
| title | Contrastive learning enhanced pseudo-labeling for unsupervised domain adaptation in person re-identification. |
| title_full | Contrastive learning enhanced pseudo-labeling for unsupervised domain adaptation in person re-identification. |
| title_fullStr | Contrastive learning enhanced pseudo-labeling for unsupervised domain adaptation in person re-identification. |
| title_full_unstemmed | Contrastive learning enhanced pseudo-labeling for unsupervised domain adaptation in person re-identification. |
| title_short | Contrastive learning enhanced pseudo-labeling for unsupervised domain adaptation in person re-identification. |
| title_sort | contrastive learning enhanced pseudo labeling for unsupervised domain adaptation in person re identification |
| url | https://doi.org/10.1371/journal.pone.0328131 |
| work_keys_str_mv | AT xuemeibai contrastivelearningenhancedpseudolabelingforunsuperviseddomainadaptationinpersonreidentification AT yuqingzhang contrastivelearningenhancedpseudolabelingforunsuperviseddomainadaptationinpersonreidentification AT chenjiezhang contrastivelearningenhancedpseudolabelingforunsuperviseddomainadaptationinpersonreidentification AT zhijunwang contrastivelearningenhancedpseudolabelingforunsuperviseddomainadaptationinpersonreidentification |