Skip to main content
SpringerLink
Log in

Unsupervised person reidentification via quantitative random selection for cluster centroid

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Person reidentification (re-ID) is an important topic in computer vision. This paper studies an unsupervised approach to re-ID, which does not require any labeled information and is thus possible to deploy in real-world scenarios. State-of-the-art unsupervised re-ID methods usually use a memory bank to store the instance feature vectors, generate pseudolabels with a clustering algorithm, and compare the query instances to the centroid of the clusters for contrastive learning. However, because hard negative or noisy samples exist, the centroid generated by unsupervised learning may not be a perfect prototype. Forcing the wrong images to get closer to the centroid would result in accumulated errors and deteriorated overfitting. To solve this problem, we propose a quantitative random selection strategy to form the cluster feature representation. Specifically, in each iteration, the cluster algorithm executes on instance-level feature vectors to generate pseudolabels. Then, we shuffle all the instance vectors belonging to the same cluster and select samples within the same cluster in a certain proportion to form the cluster-level memory. During network training, the query instances are used to update the cluster-level memory for contrastive learning. Extensive experiments show that our proposed method produces state-of-the-art performance in unsupervised person re-ID tasks.

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

Similar content being viewed by others

References

  1. Sun Y, Zheng L, Yang Y, Tian Q, Wang S (2018) Beyond part models: Person retrieval with refined part pooling. In: Proceedings of the European conference on computer vision

  2. Su C, Li J, Zhang S, Xing J, Gao W, Tian Q (2017) Pose-driven deep convolutional model for person re-identification. In: ICCV

  3. Tian H, Zhang X, Lan L, Luo Z (2019) Person re-identification via adaptive verification loss. Neurocomputing 359:93–101

    Article  Google Scholar 

  4. Fan H, Zheng L, Yan C, Yang Y (2018) Unsupervised person re-identification Clustering and finetuning. ACM Trans Multimed Comput Commun Appl 14(4):1–18

    Article  Google Scholar 

  5. 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

  6. 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: ACM SIGKDD Conference on Knowledge Discovery and Data Mining, vol 96, pp 226–231

  7. MacQueen J et al (1967) Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, vol 1, pp 281–297

  8. Liu X, Zhu X, Li M et al (2017) Multiple Kernel k-means with Incomplete Kernels. In: AAAI, pp 1–1

  9. Yu X, Ye X, Gao Q (2019) Pipeline image segmentation algorithm and heat loss calculation based on gene-regulated apoptosis mechanism. In: International Journal of Pressure Vessels and Piping, vol 172

  10. Yu X, Lu YH, Gao Q (2021) Pipeline image diagnosis algorithm based on neural immune ensemble learning. Int J Press Vessel Pip 104249:189

    Google Scholar 

  11. Ristani E, Solera F, Zou R, Cucchiara R, Tomasi C (2016) Performance measures and a data set for multi-target, multi-camera tracking. In: ECCV, pp 17–35

  12. Zheng L, Shen L, Tian L, Wang S, Wang J, Tian Q (2015) Scalable person re-identification: A benchmark. In: ICCV, pp 1116–1124

  13. Wu Z, Xiong Y, Yu SX, Lin D (2018) Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3733–3742

  14. 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

  15. Zou Y, Yang X, Yu Z, Kumar BVK, Kautz J (2020) Joint disentangling and adaptation for crossdomain person re-identification. In: Proceedings of the European conference on computer vision

  16. Zheng K, Lan C, Zeng W, Zhang Z, Zha Z-J (2021) Exploiting sample uncertainty for domain adaptive person re-identification. In: AAAI, pp 3538–3546

  17. Deng W, Zheng L, Ye Q, Kang G, Yang Y, Jiao J (2018) Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition

  18. Xuan S, Zhang S (2021) Intra-inter camera similarity for unsupervised person re-identification. In: CVPR, pp 11926–11935

  19. 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

  20. Ge Y, Zhu F, Chen D, Zhao R, Li H (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

  21. Liu X, Zhang S (2021) Graph consistency based mean-teaching for unsupervised domain adaptive person re-identification. In: IJCAI, pp 874–880

  22. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR, pp 770–778

  23. Dai Z, Wang G, Yuan W et al (2021) Cluster Contrast for Unsupervised Person Re-Identification, arXiv:2103.11568

  24. He K, Fan H, Wu Y, Xie S, Girshick R (2020) Momentum contrast for unsupervised visual representation learning. In: CVPR, pp 9729–9738

  25. Zheng K, Liu W, He L, Mei T, Luo J, Zha Z-J (2021) Group-aware label transfer for domain adaptive person re-identification. In: CVPR, pp 5310–5319

  26. Zheng Y, Tang S, Teng G, Ge Y, Liu K, Qin J, Qi D, Chen D (2021) Online pseudo label generation by hierarchical cluster dynamics for adaptive person re-identification. In: ICCV, pp 8371–8381

  27. Wu Y, Wu X, Li X, Tian J (2021) MGH:metadata guided hypergraph modeling for unsupervised person re-identification. In: ACM Multimedia, pp 1571–1580

  28. Chen H, Lagadec B, Bremond F (2021) ICE: Inter-instance contrastive encoding for unsupervised person re-identification. arXiv:2103.16364

  29. Zhang Z, Lan C, Zeng W, Jin X, Chen Z (2020) Relation-aware global attention for person re-identification. In: CVPR, pp 3186–3195

  30. Zhong Z, Zheng L, Luo Z, Li S, Yang Y (2020) Learning to adapt invariance in memory for person re-identification. IEEE Transactions on Pattern Analysis and Machine Intelligence PP(99):1–1

    Article  Google Scholar 

  31. Yu HX, Zheng WS, Wu A, Guo X, Lai JH (2019) Unsupervised person re-identification by soft multilabel learning. In: CVPR

  32. Fu Y, Wei Y, Wang G, Zhou Y, Shi H, Huang TS (2019) Self-similarity grouping: A simple unsupervised cross domain adaptation approach for person re-identification. In: ICCV, pp 6112–6121

  33. 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: CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions

  34. Zhai Y, Lu S, Ye Q, Shan X, Tian Y (2020) Ad-cluster: Augmented discriminative clustering for domain adaptive person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition

  35. Li J, Zhang S (2020) Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-Identification

  36. Zou Y, Yang X, Yu Z, Kumar B, Kautz J (2020) Joint disentangling and adaptation for cross-domain person re-identification. In: Proceedings of the European conference on computer vision

  37. Ge Y, Chen D, Li H (2020) Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification. In: International conference on learning representations

  38. Chen G, Lu Y, Lu J, Zhou J (2020) Deep credible metric learning for unsupervised domain adaptation person re-identification. In: Proceedings of the European conference on computer vision, pp 643–659

  39. 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

  40. 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

  41. Wu J, Yang Y, Liu H, Liao S, Lei Z, Li S (2019) Unsupervised graph association for person re-identification. In: ICCV, pp 8321–8330

  42. Lin Y, Xie L, Wu Y, Yan C, Tian Q (2020) Unsupervised person re-identification via softened similarity learning. In: CVPR, pp 3390–3399

  43. Wang D, Zhang S (2020) Unsupervised person re-identification via multi-label classification. In: CVPR

  44. Zeng K, Ning M, Wang Y, Guo Y (2020) Hierarchical clustering with hard-batch triplet loss for person re-identification. In: CVPR, pp 657–665

  45. Wang M, Lai B, Huang J, Gong X, Hua X-S (2021) Camera-aware proxies for unsupervised person re-identification. In: AAAI

Download references

Funding

This work is supported by the National Natural Science Foundation of China (Grant No. U1833115).

Author information

Authors and Affiliations

  1. National Key Laboratory of Fundamental Science on Synthetic Vision, College of Computer Science, Sichuan University, Chengdu, China

    Xin Zhang & Ziliang Feng

  2. College of Computer Science, Sichuan University, Chengdu, China

    Xin Zhang & Ziliang Feng

Authors
  1. Xin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ziliang Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xin Zhang.

Ethics declarations

Conflict of Interests

The authors declare that they have no conflicts of interest.

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 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

Zhang, X., Feng, Z. Unsupervised person reidentification via quantitative random selection for cluster centroid. Appl Intell 53, 10726–10733 (2023). https://doi.org/10.1007/s10489-022-03439-x

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-03439-x

Keywords

Search

Navigation