这是indexloc提供的服务，不要输入任何密码
Skip to main content
Springer Nature Link
Log in

RULER: Source-free Domain Adaptive Person Re-identification via Uncertain Label Refinery

  • Research Article
  • Published:
Machine Intelligence Research Aims and scope Submit manuscript

Abstract

Source-free domain adaptive person re-identification (ReID) aims to address the cross-domain person ReID task with a well-trained source model, which solves the limitations of data privacy and transmission costs in real-world scenarios. Existing methods mainly generate pseudo labels for target data, which are unreliable because of distribution shifts. First, the ubiquitous difficult samples may lead to the ambiguity of the model prediction. Second, the source model may have a bias towards certain classes. To alleviate these two problems, we propose a source-free domain adaptive person ReID method via the uncertain label refinery (RULER). RULER consists of uncertainty-aware pseudo-labeling refinery (UPLR) and frequency-weighted contrastive learning (FCL). To reduce the ambiguity of predictions caused by sample label uncertainty, UPLR generates pseudo labels by clustering samples after multiple random dropouts and then integrates the results to obtain high-confidence pseudo labels. Moreover, FCL defines the frequency of each class as the sample weight and introduces a frequency-weighted contrastive loss to alleviate the class biases of the model. RULER improves the quality of pseudo labels and mitigates the source model′s bias towards certain classes. We achieve competitive results compared to state-of-the-art methods on both real-to-real and synthetic-to-real source-free domain adaptation scenarios, validating the effectiveness of RULER.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+
from $39.99 /Month
  • Starting from 10 chapters or articles per month
  • Access and download chapters and articles from more than 300k books and 2,500 journals
  • Cancel anytime
View plans

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Explore related subjects

Discover the latest articles, books and news in related subjects, suggested using machine learning.

References

  1. M. Ye, J. Shen, G. Lin, T. Xiang, L. Shao, S. C. H. Hoi. Deep learning for person Re-identification: A survey and outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 6, pp. 2872–2893, 2022. DOI: https://doi.org/10.1109/TPAMI.2021.3054775.

    Article  Google Scholar 

  2. K. Zhou, T. Xiang. Torchreid: A library for deep learning person re-identification in Pytorch, [Online], Available: https://arxiv.org/abs/1910.10093, 2019.

    Google Scholar 

  3. Z. Yu, Y. Zhao, B. Hong, Z. Jin, J. Huang, D. Cai, X. S. Hua. Apparel-invariant feature learning for person re-identification. IEEE Transactions on Multimedia, vol. 24, pp. 4482–4492, 2022. DOI: https://doi.org/10.1109/TMM.2021.3119133.

    Article  Google Scholar 

  4. P. Yan, X. Liu, P. Zhang, H. Lu. Learning convolutional multi-level transformers for image-based person re-identification. Visual Intelligence, vol. 1, no. 1, Article number 24, 2023. DOI: https://doi.org/10.1007/s44267-023-00025-8.

    Article  Google Scholar 

  5. K. Niu, T. Huang, L. Huang, L. Wang, Y. Zhang. Improving inconspicuous attributes modeling for person search by language. IEEE Transactions on Image Processing, vol. 32, pp. 3429–3441, 2023. DOI: https://doi.org/10.1109/TIP.2023.3285426.

    Article  Google Scholar 

  6. K. Niu, L. Huang, Y. Long, Y. Huang, L. Wang, Y. Zhang. Comprehensive attribute prediction learning for person search by language. IEEE Transactions on Image Processing, vol. 33, pp. 1990–2003, 2024. DOI: https://doi.org/10.1109/TIP.2024.3372832.

    Article  Google Scholar 

  7. A. Zheng, P. Pan, H. Li, C. Li, B. Luo, C. Tan, R. Jia. Progressive attribute embedding for accurate cross-modality person Re-ID. In Proceedings of the 30th ACM International Conference on Multimedia, Lisboa, Portugal, pp. 4309–4317, 2022. DOI: https://doi.org/10.1145/3503161.3548336.

    Chapter  Google Scholar 

  8. A. X. Li, K. X. Zhang, L. W. Wang. Zero-shot fine-grained classification by deep feature learning with semantics. International Journal of Automation and Computing, vol. 16, no. 5, pp. 563–574, 2019. DOI: https://doi.org/10.1007/s11633-019-1177-8.

    Article  Google Scholar 

  9. M. Kutbi, K. C. Peng, Z. Wu. Zero-shot deep domain adaptation with common representation learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 7, pp. 3909–3924, 2022. DOI: https://doi.org/10.1109/TPAMI.2021.3061204.

    Google Scholar 

  10. M. J. Mirza, J. Micorek, H. Possegger, H. Bischof. The norm must go on: Dynamic unsupervised domain adaptation by normalization. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, pp. 14745–14755, 2022. DOI: https://doi.org/10.1109/CVPR52688.2022.01435.

    Google Scholar 

  11. H. Chen, Y. Wang, B. Lagadec, A. Dantcheva, F. Bremond. Joint generative and contrastive learning for unsupervised person re-identification. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA, pp. 2004–2013, 2021. DOI: https://doi.org/10.1109/CVPR46437.2021.00204.

    Google Scholar 

  12. Y. Dai, J. Liu, Y. Sun, Z. Tong, C. Zhang, L. Y. Duan. IDM: An intermediate domain module for domain adaptive person Re-ID. In Proceedings of IEEE/CVF International Conference on Computer Vision, Montreal, Canada, pp. 11844–11854, 2021. DOI: https://doi.org/10.1109/ICCV48922.2021.01165.

    Google Scholar 

  13. J. Sun, Y. Li, H. Chen, X. Zhu, Y. Peng, Y. Peng. Intercluster and intra-cluster joint optimization for unsupervised cross-domain person re-identification. Knowledge-Based Systems, vol. 251, Article number 109162, 2022. DOI: https://doi.org/10.1016/j.knosys.2022.109162.

    Article  Google Scholar 

  14. Y. Tao, J. Zhang, J. Hong, Y. Zhu. DREAMT: Diversity enlarged mutual teaching for unsupervised domain adaptive person re-identification. IEEE Transactions on Multimedia, vol. 25, pp. 4586–4597, 2023. DOI: https://doi.org/10.1109/TMM.2022.3178599.

    Article  Google Scholar 

  15. Y. Wu, T. Huang, H. Yao, C. Zhang, Y. Shao, C. Han, C. Gao, N. Sang. Multi-centroid representation network for domain adaptive person Re-ID. In Proceedings of the 36th AAAI Conference on Artificial Intelligence, pp. 2750–2758, 2022. DOI: https://doi.org/10.1609/aaai.v36i3.20178.

    Google Scholar 

  16. G. Lee, S. Lee, D. Kim, Y. Shin, Y. Yoon, B. Ham. Camera-driven representation learning for unsupervised domain adaptive person re-identification. In Proceedings of IEEE/CVF International Conference on Computer Vision, Paris, France, pp. 11419–11428, 2023. DOI: https://doi.org/10.1109/ICCV51070.2023.01052.

    Google Scholar 

  17. J. Liang, D. Hu, J. Feng. Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation. In Proceedings of the 37th International Conference on Machine Learning, Article number 560, 2020.

    Google Scholar 

  18. X. Qu, H. Zhang, L. Zhu, L. Nie, L. Liu. AAMT: Adversarial attack-driven mutual teaching for source-free domain-adaptive person reidentification. IEEE Transactions on Multimedia, vol. 26, pp. 8255–8267, 2024. DOI: https://doi.org/10.1109/TMM.2024.3379096.

    Article  Google Scholar 

  19. X. Qu, L. Liu, L. Zhu, L. Nie, H. Zhang. Instance-level adversarial source-free domain adaptive person re-identification. ACM Transactions on Multimedia Computing, Communications and Applications, vol. 20, no. 7, Article number 197, 2024. DOI: https://doi.org/10.1145/36499.

    Article  Google Scholar 

  20. X. Qu, L. Liu, L. Zhu, L. Nie, H. Zhang. Source-free stylediversity adversarial domain adaptation with privacy-preservation for person re-identification. Knowledge-Based Systems, vol. 283, Article number 111150, 2024. DOI: https://doi.org/10.1016/j.knosys.2023.111150.

    Article  Google Scholar 

  21. F. Chen, N. Wang, J. Tang, P. Yan, J. Yu. Unsupervised person re-identification via multi-domain joint learning. Pattern Recognition, vol. 138, Article number 109369, 2023. DOI: https://doi.org/10.1016/j.patcog.2023.109369.

    Article  Google Scholar 

  22. J. Han, Y. L. Li, S. Wang. Delving into probabilistic uncertainty for unsupervised domain adaptive person reidentification. In Proceedings of the 36th AAAI Conference on Artificial Intelligence, pp. 790–798, 2022. DOI: https://doi.org/10.1609/aaai.v36i1.19960.

    Google Scholar 

  23. H. Chen, B. Lagadec, F. Brémond. Enhancing diversity in teacher-student networks via asymmetric branches for unsupervised person re-identification. In Proceedings of IEEE Winter Conference on Applications of Computer Vision, Waikoloa, USA, 2021. DOI: https://doi.org/10.1109/WACV48630.2021.00005.

    Google Scholar 

  24. Y. Ge, D. Chen, H. Li. Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification. In Proceedings of the 8th International Conference on Learning Representations, Addis Ababa, Ethiopia, 2020.

    Google Scholar 

  25. J. MacQueen. Some methods for classification and analysis of multivariate observations. In Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability, Oakland, USA, pp. 281–297, 1967.

    Google Scholar 

  26. M. Ester, H. P. Kriegel, J. Sander, X. Xu. A density-based algorithm for discovering clusters in large spatial databases with noise. In Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining, Portland, Oregon, pp. 226–231, 1996.

    Google Scholar 

  27. L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, Q. Tian. Scalable person re-identification: A benchmark. In Proceedings of IEEE International Conference on Computer Vision, Santiago, Chile, pp. 1116–1124, 2015. DOI: https://doi.org/10.1109/ICCV.2015.133.

    Google Scholar 

  28. L. Wei, S. Zhang, W. Gao, Q. Tian. Person transfer GAN to bridge domain gap for person re-identification. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, pp. 79–88, 2018. DOI: https://doi.org/10.1109/CVPR.2018.00016.

    Google Scholar 

  29. M. Buda, A. Maki, M. A. Mazurowski. A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks, vol. 106, pp. 249–259, 2018. DOI: https://doi.org/10.1016/j.neunet.2018.07.011.

    Article  Google Scholar 

  30. C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, R. Garnett. Advances in neural information processing systems 28. In Proceedings of the 29th Annual Conference on Neural Information Processing Systems, Montreal, Canada, 2015.

    Google Scholar 

  31. J. Y. Zhu, T. Park, P. Isola, A. A. Efros. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of IEEE Transactions on Pattern Analysis and Machine Intelligence, Venice, Italy, pp. 2223–2232, 2017.

    Google Scholar 

  32. W. Deng, L. Zheng, Q. Ye, G. Kang, Y. Yang, J. Jiao. Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, pp. 994–1003, 2018. DOI: https://doi.org/10.1109/CVPR.2018.00110.

    Google Scholar 

  33. Y. Zou, X. Yang, Z. Yu, B. V. K. V. Kumar, J. Kautz. Joint disentangling and adaptation for cross-domain person re-identification. In Proceedings of the 16th European Conference on Computer Vision, Glasgow, UK, pp. 87–104, 2020. DOI: https://doi.org/10.1007/978-3-030-58536-5_6.

    Google Scholar 

  34. Y. Ge, F. Zhu, D. Chen, R. Zhao, H. Li. Self-paced contrastive learning with hybrid memory for domain adaptive object re-ID. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 949, 2020.

    Google Scholar 

  35. Y. Zhang, F. Zhang, Y. Jin, Y. Cen, V. Voronin, S. Wan. Local correlation ensemble with GCN based on attention features for cross-domain person Re-ID. ACM Transactions on Multimedia Computing, Communications and Applications, vol. 19, no. 2, Article number 56, 2023. DOI: https://doi.org/10.1145/3542820.

    Article  Google Scholar 

  36. J. Liang, D. Hu, Y. Wang, R. He, J. Feng. Source data-absent unsupervised domain adaptation through hypothesis transfer and labeling transfer. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 11, pp. 8602–8617, 2022. DOI: https://doi.org/10.1109/TPAMI.2021.3103390.

    Google Scholar 

  37. A. Hermans, L. Beyer, B. Leibe. In defense of the triplet loss for person re-identification, [Online], Available: https://arxiv.org/abs/1703.07737, 2017.

    Google Scholar 

  38. Y. Gal, Z. Ghahramani. Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the 33rd International Conference on Machine Learning, New York, USA, pp. 1050–1059, 2016.

    Google Scholar 

  39. H. W. Kuhn. The Hungarian method for the assignment problem. Naval Research Logistics Quarterly, vol. 2, no. 1–2, pp. 83–97, 1955. DOI: https://doi.org/10.1002/nav.3800020109.

    Article  MathSciNet  Google Scholar 

  40. Z. Dai, G. Wang, W. Yuan, S. Zhu, P. Tan. Cluster contrast for unsupervised person re-identification. In Proceedings of the 16th Asian Conference on Computer Vision, Macao, China, pp. 319–337, 2022. DOI: https://doi.org/10.1007/978-3-031-26351-4_20.

    Google Scholar 

  41. D. Wang, S. Zhang. Unsupervised person re-identification via multi-label classification. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, pp. 10978–10987, 2020. DOI: https://doi.org/10.1109/CVPR42600.2020.01099.

    Google Scholar 

  42. J. Chen, C. Gao, L. Sun, N. Sang. CCSD: Cross-camera self-distillation for unsupervised person re-identification. Visual Intelligence, vol. 1, no. 1, Article number 27, 2023. DOI: https://doi.org/10.1007/s44267-023-00029-4.

    Article  Google Scholar 

  43. H. Lu, Y. Huo, M. Ding, N. Fei, Z. Lu. Cross-modal contrastive learning for generalizable and efficient image-text retrieval. Machine Intelligence Research, vol. 20, no. 4, pp. 569–582, 2023. DOI: https://doi.org/10.1007/s11633-022-1386-4.

    Article  Google Scholar 

  44. W. C. Wang, E. Ahn, D. Feng, J. Kim. A review of predictive and contrastive self-supervised learning for medical images. Machine Intelligence Research, vol. 20, no. 4, pp. 483–513, 2023. DOI: https://doi.org/10.1007/s11633-022-1406-4.

    Article  Google Scholar 

  45. D. Y. She, K. Xu. Contrastive self-supervised representation learning using synthetic data. International Journal of Automation and Computing, vol. 18, no. 4, pp. 556–567, 2021. DOI: https://doi.org/10.1007/s11633-021-1297-9/.

    Article  Google Scholar 

  46. A. van den Oord, Y. Li, O. Vinyals. Representation learning with contrastive predictive coding, [Online], Available: https://arxiv.org/abs/1807.03748, 2018.

    Google Scholar 

  47. Z. Wu, Y. Xiong, S. X. Yu, D. Lin. Unsupervised feature learning via non-parametric instance discrimination. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, pp. 3733–3742, 2018. DOI: https://doi.org/10.1109/CVPR.2018.00393.

    Google Scholar 

  48. Z. Zheng, L. Zheng, Y. Yang. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In Proceedings of IEEE International Conference on Computer Vision, Venice, Italy, pp. 3774–3782, 2017. DOI: https://doi.org/10.1109/ICCV.2017.405.

    Google Scholar 

  49. E. Ristani, F. Solera, R. Zou, R. Cucchiara, C. Tomasi. Performance measures and a data set for multi-target, multi-camera tracking. Computer Vision-ECCV Workshops, G. Hua, H. Jégou, Eds., Cham, Switzerland: Springer, pp. 17–35, 2016. DOI: https://doi.org/10.1007/978-3-319-48881-3_2.

    Google Scholar 

  50. T. Zhang, L. Xie, L. Wei, Z. Zhuang, Y. Zhang, B. Li, Q. Tian. UnrealPerson: An adaptive pipeline towards costless person re-identification. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA, pp. 11501–11510, 2021. DOI: https://doi.org/10.1109/CVPR46437.2021.01134.

    Google Scholar 

  51. K. He, X. Zhang, S. Ren, J. Sun. Deep residual learning for image recognition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 770–778, 2016. DOI: https://doi.org/10.1109/CVPR.2016.90.

    Google Scholar 

  52. J. Deng, W. Dong, R. Socher, L. J. Li, K. Li, Li F. F. ImageNet: A large-scale hierarchical image database. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, Miami, USA, pp. 248–255, 2009.

    Google Scholar 

  53. D. P. Kingma, J. Ba. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations, San Diego, USA, 2014.

    Google Scholar 

  54. Z. Zhong, L. Zheng, G. Kang, S. Li, Y. Yang. Random erasing data augmentation. In Proceedings of the 34th AAAI Conference on Artificial Intelligence, New York, USA, pp. 13001–13008, 2020. DOI: https://doi.org/10.1609/aaai.v34i07.7000.

    Google Scholar 

  55. Y. Zheng, S. Tang, G. Teng, Y. Ge, K. Liu, J. Qin, D. Qi, D. Chen. Online pseudo label generation by hierarchical cluster dynamics for adaptive person re-identification. In Proceedings of IEEE/CVF International Conference on Computer Vision, Montreal, Canada, pp. 8351–8361, 2021. DOI: https://doi.org/10.1109/ICCV48922.2021.00826.

    Google Scholar 

  56. L. van der Maaten, G. Hinton. Visualizing data using t-SNE. Journal of Machine Learning Research, vol. 9, no. 86, pp. 2579–2605, 2008

    Google Scholar 

Download references

Acknowledgements

This work was supported in part by the National Natural Science Foundation of China (Nos. 62372003 and 62376004), the Natural Science Foundation of Anhui Province, China (Nos. 2308085Y40 and 2208085J18), and the University Synergy Innovation Program of Anhui Province, China (No. GXXT-2022-036).

Author information

Authors and Affiliations

  1. Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei, 230601, China

    Aihua Zheng, Zhihao Fei & Chenglong Li

  2. Anhui Provincial Key Laboratory of Multi-modal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, 230601, China

    Yuhe Ding & Bin Luo

Authors
  1. Aihua Zheng
    View author publications

    Search author on:PubMed Google Scholar

  2. Zhihao Fei
    View author publications

    Search author on:PubMed Google Scholar

  3. Yuhe Ding
    View author publications

    Search author on:PubMed Google Scholar

  4. Chenglong Li
    View author publications

    Search author on:PubMed Google Scholar

  5. Bin Luo
    View author publications

    Search author on:PubMed Google Scholar

Corresponding author

Correspondence to Chenglong Li.

Ethics declarations

The authors declared that they have no conflicts of interest to this work.

Additional information

Colored figures are available in the online version at https://link.springer.com/journal/11633

Aihua Zheng received the B. Eng. degree and finished Master-Doctor Combined Program in computer science and technology from Anhui University, China in 2006 and 2008, respectively, and the Ph. D. degree in computer science from University of Greenwich, UK in 2012. She visited University of Stirling, UK during June to September in 2013 and Texas State University, USA during September 2019 to August 2020, respectively. She is currently a professor and the Ph. D. supervisor at the School of Artificial Intelligence, Anhui University, China.

Her research interests include person/vehicle re-identification, audio-visual computing, and multi-modal intelligence.

Zhihao Fei received the B. Eng. degree in computer science and technology from West Anhui University, China in 2022, and is currently a master student in the School of Artificial Intelligence, Anhui University, China.

His research interests include computer vision, domain adaptation and person reidentification.

Yuhe Ding received the B. Eng. degree in computer science from Anhui University, China in 2019. She is currently a Ph. D. degree candidate in the School of Computer Science and Technology, Anhui University, China. From 2020 to 2022, she was a visiting student at Institute of Automation, Chinese Academy of Sciences, China.

Her research interests include transfer learning, pattern recognition, and computer vision.

Chenglong Li received the M. Sc. and Ph. D. degrees in computer application technology from the School of Computer Science and Technology, Anhui University, China in 2013 and 2016, respectively. From 2014 to 2015, he worked as a visiting student with the School of Data and Computer Science, Sun Yat-sen University, China. He was a postdoctoral research fellow at the Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), China. He is currently a professor and Ph. D. supervisor at the School of Artificial Intelligence, Anhui University, China. He was a recipient of the ACM Hefei Doctoral Dissertation Award in 2016.

His research interests include computer vision and deep learning.

Bin Luo received the B. Eng. degree in electronics and the M. Eng. degree in computer science from the Anhui University, China in 1984 and 1991, respectively, and the Ph. D. degree in computer science from the University of York, UK in 2002. He has authored or coauthored more than 200 papers in journals and refereed conferences. He is currently a professor with the Anhui University, China. He is currently the Chair of the IEEE Hefei Subsection. He was a peer reviewer of international academic journals, such as IEEE Transactions on Pattern Analysis and Machine Intelligence, Pattern Recognition, and Pattern Recognition Letters.

His research interests include random graph-based pattern recognition, image and graph matching, and spectral analysis.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zheng, A., Fei, Z., Ding, Y. et al. RULER: Source-free Domain Adaptive Person Re-identification via Uncertain Label Refinery. Mach. Intell. Res. 22, 900–916 (2025). https://doi.org/10.1007/s11633-025-1543-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1007/s11633-025-1543-7

Keywords