Skip to main content
SpringerLink
Log in

A new robust contrastive learning for unsupervised person re-identification

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Unsupervised person re-identification (Re-ID) is more substantial than the supervised one because it does not require any labeled samples. Currently, the most advanced unsupervised Re-ID models generate pseudo-labels to group images into different clusters and then establish a memory bank to calculate contrastive loss between instances and clusters. This framework has been proven to be remarkably efficient for unsupervised person Re-ID tasks. However, clustering operation inevitably produces misclassification, which brings noises and difficulties to contrastive learning and affects the initialization and updating of the prototype features stored in the memory bank. To solve this problem, we propose a new robust unsupervised person Re-ID model with two developed modules: Cluster Sample Aggregation module (CSA) and Hard Positive Sampling strategy (HPS). The CSA module aggregates each sample in the same cluster through the multi-head self-attention mechanism. This process enables the initialization of prototypes based on the similarities observed within clusters. Additionally, the HPS strategy extracts the dispersion degree of each sample by means of a self-attention aggregation module (SAA) that has been trained by CSA module. According to the obtained indicators, the hardest positive sample is sampled to update the prototype feature stored in the memory bank. With the self-attention mechanism fusing the information among instances in each cluster, the implicit relationships between samples can be better explored in a more refined way. Experiments show that our method achieves state-of-the-art results against existing unsupervised baselines on Market-1501, PersonX, and MSMT17 datasets.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Data availability

The dataset used in this paper is publicly accessible based on cited references. In addition, the data that support the findings of this study are available on request from the first author, [Huibin Lin], upon reasonable request.

References

  1. Zhai Y, Ye Q, Lu S, Jia M, Ji R, Tian Y (2020) Multiple expert brainstorming for domain adaptive person re-identification. In: Proceedings of the European Conference on computer vision, pp 594–611

  2. Song X, Jin Z (2022) Domain adaptive attention-based dropout for one-shot person re-identification. Int J Mach Learn Cybern 13:255–268

    Article  Google Scholar 

  3. Ge Y, Zhu F, Chen D, Zhao R, et al (2020) Self-paced contrastive learning with hybrid memory for domain adaptive object re-id. In: Advances in neural information processing systems, vol. 33, pp 11309–11321

  4. Yao H, Xu C (2021) Dual cluster contrastive learning for object re-identification. arXiv preprint arXiv:2112.04662

  5. Hu Z, Zhu C, He G (2021) Hard-sample guided hybrid contrast learning for unsupervised person re-identification. In: 2021 7th IEEE International Conference on network intelligence and digital content, pp 91–95

  6. Chen H, Lagadec B, Bremond F (2021) Ice: inter-instance contrastive encoding for unsupervised person re-identification. In: Proceedings of the IEEE International Conference on computer vision, pp 14960–14969

  7. Ester M, Kriegel H-P, Sander J, Xu X, et al (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Kdd, vol. 96, pp. 226–231

  8. Xie K, Wu Y, Xiao J, Li J, Xiao G, Cao Y (2021) Unsupervised person re-identification via k-reciprocal encoding and style transfer. Int J Mach Learn Cybern 12:2899–2916

    Article  Google Scholar 

  9. Bachman P, Hjelm RD, Buchwalter W (2019) Learning representations by maximizing mutual information across views. In: Advances in neural information processing systems, vol. 32

  10. Tian Y, Krishnan D, Isola P (2020) Contrastive multiview coding. In: Proceedings of the European Conference on computer vision, pp 776–794

  11. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 770–778

  12. Zhong Z, Zheng L, Luo Z, Li S, Yang Y (2019) Invariance matters: exemplar memory for domain adaptive person re-identification. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 598–607

  13. Lin Y, Dong X, Zheng L, Yan Y, Yang Y (2019) A bottom-up clustering approach to unsupervised person re-identification. In: Proceedings of the AAAI Conference on artificial intelligence, vol. 33, pp 8738–8745

  14. Dai Z, Wang G, Zhu S, Yuan W, Tan P (2021) Cluster contrast for unsupervised person re-identification. arXiv preprint arXiv:2103.11568

  15. Oord A, Li Y, Vinyals O (2018) Representation learning with contrastive predictive coding. arXiv e-prints, 1807

  16. Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 815–823

  17. Wang D, Zhang S (2020) Unsupervised person re-identification via multi-label classification. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 10981–10990

  18. Ren Z, Zhang Y, Wang S (2022) Lcdae: data augmented ensemble framework for lung cancer classification. Technol Cancer Res Treat 21:1–14

    Article  Google Scholar 

  19. Xiao T, Li S, Wang B, Lin L, Wang X (2017) Joint detection and identification feature learning for person search. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 3415–3424

  20. He K, Fan H, Wu Y, Xie S, Girshick R (2020) Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 9729–9738

  21. Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: International Conference on machine learning, pp 1597–1607

  22. Zhang X, Ge Y, Qiao Y, Li H (2021) Refining pseudo labels with clustering consensus over generations for unsupervised object re-identification. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 3436–3445

  23. Zhou H, Kong J, Jiang M, Liu T (2023) Heterogeneous dual network with feature consistency for domain adaptation person re-identification. Int J Mach Learn Cybern 14(5):1951–1965

    Article  Google Scholar 

  24. Liu Y, Ge H, Sun L, Hou Y (2022) Complementary attention-driven contrastive learning with hard-sample exploring for unsupervised domain adaptive person re-id. IEEE Trans Circuits Syst Video Technol 33(1):326–341

    Article  Google Scholar 

  25. Ren Z, Wang S, Zhang Y (2023) Weakly supervised machine learning. CAAI Trans Intell Technol 8:1–32

  26. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems 30

  27. Touvron H, Cord M, Douze M, Massa F, Sablayrolles A, Jégou H (2021) Training data-efficient image transformers & distillation through attention. In: International Conference on machine learning, pp 10347–10357

  28. Zhang Y, Deng L, Zhu H, Wang W, Ren Z, Zhou Q, Lu S, Sun S, Zhu Z, Gorriz JM et al (2023) Deep learning in food category recognition. Inform Fusion, p 101859

  29. Cai D, Lam W (2020) Graph transformer for graph-to-sequence learning. In: Proceedings of the AAAI Conference on artificial intelligence, vol. 34, pp 7464–7471

  30. Yun S, Jeong M, Kim R, Kang J, Kim HJ (2019) Graph transformer networks. In: Advances in neural information processing systems, vol. 32

  31. Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 248–255. Ieee

  32. Zhong Z, Zheng L, Cao D, Li S (2017) Re-ranking person re-identification with k-reciprocal encoding. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 1318–1327

  33. Zheng L, Shen L, Tian L, Wang S, Wang J, Tian Q (2015) Scalable person re-identification: a benchmark. In: Proceedings of the IEEE International Conference on computer vision, pp 1116–1124

  34. Wei L, Zhang S, Gao W, Tian Q (2018) Person transfer gan to bridge domain gap for person re-identification. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 79–88

  35. Sun X, Zheng L (2019) Dissecting person re-identification from the viewpoint of viewpoint. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 608–617

  36. Riccitiello J (2015) John riccitiello sets out to identify the engine of growth for unity technologies (interview). VentureBeat. Interview with Dean Takahashi. Retrieved January 18(3)

  37. Gray D, Brennan S, Tao H (2007) Evaluating appearance models for recognition, reacquisition, and tracking. In: Proc. IEEE International Workshop on Performance Evaluation for Tracking and Surveillance (PETS), vol. 3, pp. 1–7

  38. Lin Y, Xie L, Wu Y, Yan C, Tian Q (2020) Unsupervised person re-identification via softened similarity learning. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 3390–3399

  39. Li J, Zhang S (2020) Joint visual and temporal consistency for unsupervised domain adaptive person re-identification. In: Proceedings of the European Conference on computer vision, pp 483–499

  40. Chen H, Wang Y, Lagadec B, Dantcheva A, Bremond F (2021) Joint generative and contrastive learning for unsupervised person re-identification. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 2004–2013

  41. Wang M, Lai B, Huang J, Gong X, Hua X-S (2021) Camera-aware proxies for unsupervised person re-identification. In: Proceedings of the AAAI Conference on artificial intelligence, vol. 2, p 4

  42. Li M, Li C-G, Guo J (2022) Cluster-guided asymmetric contrastive learning for unsupervised person re-identification. IEEE Trans Image Process 31:3606–3617

    Article  Google Scholar 

  43. Radenović F, Tolias G, Chum O (2018) Fine-tuning cnn image retrieval with no human annotation. IEEE Trans Pattern Anal Mach Intell 41(7):1655–1668

    Article  Google Scholar 

  44. Rosvall M, Bergstrom CT (2008) Maps of random walks on complex networks reveal community structure. Proc Natl Acad Sci 105(4):1118–1123

    Article  Google Scholar 

  45. Ge Y, Chen D, Li H (2020) Mutual mean-teaching: pseudo label refinery for unsupervised domain adaptation on person re-identification. arXiv preprint arXiv:2001.01526

  46. Li M, Zhu X, Gong S (2018) Unsupervised person re-identification by deep learning tracklet association. In: Proceedings of the European Conference on computer vision, pp 737–753

  47. Wu J, Yang Y, Liu H, Liao S, Lei Z, Li SZ (2019) Unsupervised graph association for person re-identification. In: Proceedings of the IEEE International Conference on computer vision, pp 8321–8330

  48. Wang Z, Zhang J, Zheng L, Liu Y, Sun Y, Li Y, Wang S (2020) Cycas: self-supervised cycle association for learning re-identifiable descriptions. In: Proceedings of the European Conference on computer vision, pp 72–88

Download references

Acknowledgements

This research is sponsored in part by the National Natural Science Foundation of China under Grant no. 62076065 and the Natural Science Foundation of Fujian Province under Grant no. 2020J01495.

Author information

Author notes

  1. Hai-Tao Fu, Chun-Yang Zhang have contributed equally to this work.

Authors and Affiliations

  1. College of Computer and Data Science, Fuzhou University, Fuzhou, 350116, Fujian, China

    Huibin Lin, Hai-Tao Fu & Chun-Yang Zhang

  2. School of Computer Science and Engineering, South China University of Technology, Guangzhou, 510006, Guangdong, China

    C. L. Philip Chen

Authors
  1. Huibin Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hai-Tao Fu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chun-Yang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. C. L. Philip Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Hai-Tao Fu or Chun-Yang Zhang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lin, H., Fu, HT., Zhang, CY. et al. A new robust contrastive learning for unsupervised person re-identification. Int. J. Mach. Learn. & Cyber. 15, 1779–1793 (2024). https://doi.org/10.1007/s13042-023-01997-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-023-01997-1

Keywords

Search

Navigation