Skip to main content
SpringerLink
Log in

Unsupervised person re-identification based on high-quality pseudo labels

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

The unsupervised domain adaptive (UDA) person re-identification (re-ID) method is of great significance to promote the practical application of person re-ID. However, the noisy pseudo labels in the target domain hinder its performance. In this paper, a novel high-quality pseudo labels (HQP) method for UDA person re-ID is proposed, which improves the performance from the perspectives of sample feature expression and similarity measurement in the clustering. In order to obtain better feature representation for target domain samples, a source domain generalization method based on contrastive learning (SCL) is designed. SCL learns the inherently consistent information within a sample, thereby improving the expression ability of the source domain pre-trained model. In order to provide a more reasonable similarity measurement for the clustering method, a soft label similarity based on neighborhood information integration (NII) is designed, which aids the clustering method to generate reliable pseudo labels. Market-1501, DukeMTMC-ReID and MSMT17 datasets are employed to evaluate the performance of the proposed HQP method. It achieves the results of 80.3%/92.3%, 68.0%/82.6% and 25.4/53.3 mAP/Rank-1 on DukeMTMC-ReID-to-Market-1501, Market-1501-to-DukeMTMC-ReID and DukeMTMC-ReID-to-MSMT17 tasks. Experimental results demonstrate that our HQP method performs favorably against the state-of-the-art UDA person re-ID methods.

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
Algorithm 1:
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Zhao D, Chen C, Li D (2022) Multi-stage attention and center triplet loss for person re-identication. Appl Intell 52:3077–3089. https://doi.org/10.1007/s10489-021-02511-2

    Article  Google Scholar 

  2. Lyu C, Ning W, Wang C, Wang K (2022) A multi-branch attention and alignment network for person re-identification. Appl Intell Online. https://doi.org/10.1007/s10489-021-02885-3

    Article  Google Scholar 

  3. Li M, Zhu X, Gong S (2020) Unsupervised tracklet Person re-identification. IEEE Trans Pattern Anal Mach Intell 42(7):1770–1782. https://doi.org/10.1109/TPAMI.2019.2903058

    Article  Google Scholar 

  4. Jiang K, Zhang T, Zhang Y, Wu F, Rui Y (2020) Self-supervised agent learning for unsupervised cross-domain person re-identification. IEEE Trans Image Processing 29:8549–8560. https://doi.org/10.1109/TIP.2020.3016869

    Article  MATH  Google Scholar 

  5. Cheng D, Li J, Kou Q, Zhao K, Liu R (2022) H-net: unsupervised domain adaptation person re-identification network based on hierarchy Image. Vis Comput 124:104493. https://doi.org/10.1016/j.imavis.2022.104493

    Article  Google Scholar 

  6. Wei L, Zhang S, Gao W, Tian Q (2018) Person transfer GAN to bridge domain gap for person re-identification. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 79–88. https://doi.org/10.1109/CVPR.2018.00016

  7. Li Y, Lin C, Lin Y, Wang Y (2021) Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation. IEEE/CVF International Conference on Computer Vision (ICCV), pp 7919–7929. https://doi.org/10.1109/ICCV.2019.00801

  8. Zheng D, Xiao J, Chen K, Huang X, Chen L, Zhao Y (2022) Soft pseudo-Label shrinkage for unsupervised domain adaptive person re-identification. Pattern Recogn 127:108615. https://doi.org/10.1016/j.patcog.2022.108615

    Article  Google Scholar 

  9. Zhang C, Tang Y, Zhang Z, Li D, Yang X, Zhang W (2021) Improving domain-adaptive person re-identification by dual-alignment learning with camera-aware image generation. IEEE Trans Circuits Syst Video Technol 31(11):4334–4346. https://doi.org/10.1109/TCSVT.2020.3047095

    Article  Google Scholar 

  10. Zhong Z, Zheng L, Luo Z, Li S, Yang Y (2019) Invariance matters: exemplar memory for domain adaptive person re-identification. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 598–607. https://doi.org/10.1109/CVPR.2019.00069

  11. Wu A, Zheng W, Lai J (2019) Unsupervised person re-identification by camera-aware similarity consistency learning. IEEE/CVF International Conference on Computer Vision (ICCV), pp 6922–6931. https://doi.org/10.1109/ICCV.2019.00702

  12. Liu G, Wu J (2021) Unsupervised person re-identification by intra–inter camera affinity domain adaptation. J Vis Commun Image Represent 80:103310. https://doi.org/10.1016/j.jvcir.2021.103310

    Article  Google Scholar 

  13. Xiang W, Yong H, Huang J, Hua X, Zhang L (2021) Second-order camera-aware color transformation for cross-domain person re-identification. Asian Conference on Computer Vision (ACCV), pp 36–53. https://doi.org/10.1007/978-3-030-69532-3_3

  14. Wu J, Liu H, Yang Y, Lei Z, Liao S, Li S (2019) Unsupervised graph association for person re-identification. IEEE/CVF International Conference on Computer Vision (ICCV), pp 8320–8329. https://doi.org/10.1109/ICCV.2019.00841

  15. Luo C, Song C, Zhang Z (2020) Generalizing person re-identification by camera-aware invariance learning and cross-domain mixup. European Conference on Computer Vision (ECCV), pp 224–241. https://doi.org/10.1007/978-3-030-58555-6_14

  16. Qi L, Wang L, Huo J, Zhou L, Shi Y, Gao Y (2019) A novel unsupervised camera-aware domain adaptation framework for person re-identification. IEEE/CVF International Conference on Computer Vision (ICCV), pp 8080–8089. https://doi.org/10.1109/ICCV.2019.00817

  17. Mekhazni D, Bhuiyan A, Ekladious G, Granger E (2020) Unsupervised domain adaptation in the dissimilarity space for person re-identification. European Conference on Computer Vision (ECCV), pp 159–174. https://doi.org/10.1007/978-3-030-58583-9_10

  18. Fan H, Zheng L, Yan C, Yang Y (2018) Unsupervised person re-identification: clustering and fine-tuning. ACM Trans Multim Comput 14(4):1–18. https://doi.org/10.1145/3243316

    Article  Google Scholar 

  19. Xian Y, Hu H (2018) Enhanced multi-dataset transfer learning method for unsupervised person re-identification using co-training strategy. IET Comput Vis 12(8):1219–1227. https://doi.org/10.1049/iet-cvi.2018.5103

    Article  Google Scholar 

  20. Yang F, Li K, Zhong Z, Luo Z et al (2020) Asymmetric co-teaching for unsupervised cross-domain person re-identification. Proc AAAI Conf Artif Intell 34:12597–12604

    Google Scholar 

  21. Ge Y, Zhu F, Chen D, Zhao R, Li H (2020) Self-paced contrastive learning with hybrid memory for domain adaptive object Re-ID. Conference on Neural Information Processing Systems (NeurIPS), pp 1–14

  22. Li Q, Peng X, Qiao Y, Hao Q (2022) Unsupervised person re-identification with multi-label learning guided self-paced clustering. Pattern Recogn 125:108521. https://doi.org/10.1016/j.patcog.2022.108521

    Article  Google Scholar 

  23. Zhai Y, Lu S, Ye Q, Shan X, Chen J, Ji R, Tian Y (2020) AD-cluster: augmented discriminative clustering for domain adaptive person re-identification. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 9018–9027. https://doi.org/10.1109/CVPR42600.2020.00904

  24. Yang F, Zhong Z, Luo Z et al (2021) Joint noise-tolerant learning and meta camera shift adaptation for unsupervised person re-identification. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 4853–4862. https://doi.org/10.1109/CVPR46437.2021.00482

  25. Zhu X, Li Y, Sun J, Chen H, Zhu J (2021) Unsupervised domain adaptive person re-identification via camera penalty learning. Multimed Tools Appl 80:15215–15232. https://doi.org/10.1007/s11042-021-10589-6

    Article  Google Scholar 

  26. Ge Y, Chen D, Li H (2020) Mutual mean-teaching: pseudo label refinery for unsupervised domain adaptation on person re-identification. International Conference on Learning Representations (ICLR), pp 1–15

  27. Zhao F, Liao S, Xie G, Zhao J, Zhang K, Shao L (2020) Unsupervised domain adaptation with noise resistible mutual-training for person re-identification. European Conference on Computer Vision (ECCV), pp 526–544. https://doi.org/10.1007/978-3-030-58621-8_31

  28. Zhai Y, Ye Q, Lu S, Jia M, Ji R, Tian Y (2020) Multiple expert brainstorming for domain adaptive person re-identification. European Conference on Computer Vision (ECCV), pp 594–611. https://doi.org/10.1007/978-3-030-58571-6_35

  29. Zhu X, Li Y, Sun J, Chen H, Zhu J (2021) Learning with noisy labels method for unsupervised domain adaptive person re-identification. Neurocomputing 452:78–88. https://doi.org/10.1016/j.neucom.2021.04.120

    Article  Google Scholar 

  30. Li Y, Yao H, Xu C (2021) TEST: Triplet ensemble student-teacher model for unsupervised person re-identification. IEEE Trans Image Process 30:7952–7963. https://doi.org/10.1109/TIP.2021.3112039

    Article  Google Scholar 

  31. Dai Y, Liu J, Bai Y, Tong Z, Duan L (2021) Dual-refinement: joint label and feature refinement for unsupervised domain adaptive person re-identification. IEEE Trans Image Process 30:7815–7829. https://doi.org/10.1109/TIP.2021.3104169

    Article  Google Scholar 

  32. Li Y, Yao H, Xu C (2022) Intra-domain consistency enhancement for unsupervised person re-identification. IEEE Trans Multimedia 24:415–425. https://doi.org/10.1109/TMM.2021.3052354

    Article  Google Scholar 

  33. Chen H, Wang Y, Lagadec B, Dantcheva A, Francois B (2021) Joint generative and contrastive learning for unsupervised person re-identification. IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), pp 2004-2013. https://doi.org/10.1109/CVPR46437.2021.00204

  34. Pan X, Luo P, Shi J, Tang X (2018) Two at once: enhancing learning and generalization capacities via IBN-Net[C]. European Conference on Computer Vision (ECCV) 484–500. https://doi.org/10.1007/978-3-030-01225-0_29

  35. Deng J, Dong W, Socher R, Li L, Li K, Li F (2019) ImageNet: a large-scale hierarchical image database. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 248–255. https://doi.org/10.1109/CVPR.2009.5206848

  36. Zheng L, Shen L, Tian L, Wang S, Wang J, Tian Q (2015) Scalable person re-identification: a benchmark. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 1116–1124. https://doi.org/10.1109/ICCV.2015.133

  37. Zheng Z, Zheng L, Yang Y (2017) Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. IEEE International Conference on Computer Vision (ICCV), pp 3754 – 3762. https://doi.org/10.1109/ICCV.2017.405

  38. Bolle R, Connell J, Pankanti S, Ratha N, Senior A (2005) The relation between the ROC curve and the CMC. Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID’05), pp 15–20. https://doi.org/10.1109/AUTOID.2005.48

  39. Felzenszwalb P, Mcallester D, Ramanan D (2018) A discriminatively trained, multiscale, deformable part model. IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp 1–8. https://doi.org/10.1109/CVPR.2008.4587597

  40. Ding Y, Fan H, Xu M (2020) Adaptive exploration for unsupervised person re-identification. ACM Trans Multimed Comput Commun Appl 16(1):1551–6857. https://doi.org/10.1145/3369393

    Article  Google Scholar 

  41. Yang Y, Zhuang Y, Pan Y (2021) Multiple knowledge representation for big data artificial intelligence: framework, applications, and case studies. Front Inform Technol Electron Eng 22(12):1551–1558. https://doi.org/10.1631/FITEE.2100463

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the [National Natural Science Foundation of China] (Grant numbers [62172029] and [61872030]).

Author information

Authors and Affiliations

  1. School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, 100044, China

    Yanfeng Li, Xiaodi Zhu, Jia Sun, Houjin Chen & Zhiyuan Li

Authors
  1. Yanfeng Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaodi Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jia Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Houjin Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhiyuan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yanfeng Li.

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

Li, Y., Zhu, X., Sun, J. et al. Unsupervised person re-identification based on high-quality pseudo labels. Appl Intell 53, 15112–15126 (2023). https://doi.org/10.1007/s10489-022-04270-0

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-04270-0

Keywords

Search

Navigation