Skip to main content
SpringerLink
Log in

Improving pseudo-labeling with reliable inter-camera distance encouragement for unsupervised person re-identification

  • Research Paper
  • Published:
Science China Information Sciences Aims and scope Submit manuscript

Abstract

Unsupervised person re-identification (re-ID) aims to train a discriminative model without identity annotations. State-of-the-art methods usually follow a clustering-based pipeline, which utilizes a clustering algorithm to generate pseudo-labels and performs model training iteratively. Despite the success of these methods, camera variation has not been well considered in the distance calculation step to reduce noise labels, which is the main reason for noise label generation. To address this problem, we design a plug-and-play method with low computational complexity to improve the distance calculation step in the pseudo-label generation stage. Specifically, (1) to alleviate the influence of intra-camera samples and select reliable inter-camera pairs, we propose inter-camera k-reciprocal nearest neighbor (IKNN) to mine reliable inter-camera positive pairs; and (2) to merge the relationship of reliable inter-camera pairs into the distance for better clustering, we design adaptive inter-camera encouragement (AIE) to encourage the distance of inter-camera positive pairs. Extensive experiments show consistent improvements in comparison with various state-of-the-art unsupervised re-ID methods, demonstrating the wide applicability and effectiveness of our method.

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

References

  1. Luo H, Jiang W, Gu Y Z, et al. A strong baseline and batch normalization neck for deep person re-identification. IEEE Trans Multimedia, 2016, 22: 2597–2609

    Article  Google Scholar 

  2. Sun Y F, Zheng L, Yang Y, et al. Beyond part models: person retrieval with refined part pooling. In: Proceedings of the European Conference on Computer Vision, 2018. 480–496

  3. Zheng Z D, Yang X D, Yu Z D, et al. Joint discriminative and generative learning for person re-identification. In: Proceedings of the IEEE Conference On Computer Vision and Pattern Recognition, 2019. 2138–2147

  4. Zhong Z, Zheng L, Zheng Z, et al. CamStyle: a novel data augmentation method for person re-identification. IEEE Trans Image Process, 2018, 28: 1176–1190

    Article  MathSciNet  Google Scholar 

  5. Fan H H, Zheng L, Yan C G, et al. Unsupervised person re-identification. ACM Trans Multimedia Comput Commun Appl, 2018, 14: 1–18

    Article  Google Scholar 

  6. Wu J J, Liao S C, Wang X B, et al. Clustering and dynamic sampling based unsupervised domain adaptation for person re-identification. In: Proceedings of IEEE International Conference on Multimedia and Expo, 2019. 886–891

  7. Ding Y H, Fan H H, Xu M L, et al. Adaptive exploration for unsupervised person re-identification. ACM Trans Multimedia Comput Commun Appl, 2020, 16: 1–19

    Article  Google Scholar 

  8. Zhong Z, Zheng L, Luo Z M, et al. Invariance matters: exemplar memory for domain adaptive person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019. 598–607

  9. Zeng K W, Ning M N, Wang Y H, et al. Hierarchical clustering with hard-batch triplet loss for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2020. 13657–13665

  10. Zhai Y P, Lu S J, Ye Q X, et al. AD-Cluster: augmented discriminative clustering for domain adaptive person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2020. 9021–9030

  11. Fu Y, Wei Y C, Wang G S, et al. Self-similarity grouping: a simple unsupervised cross domain adaptation approach for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, 2019. 6112–6121

  12. Zhang X Y, Cao J W, Shen C H, et al. Self-training with progressive augmentation for unsupervised cross-domain person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, 2019. 8222–8231

  13. Zhao F, Liao S C, Xie G S, et al. Unsupervised domain adaptation with noise resistible mutual-training for person reidentification. In: Proceedings of the European Conference on Computer Vision, 2020. 526–544

  14. Ge Y X, Chen D P, Li H S. Mutual mean-teaching: pseudo label refinery for unsupervised domain adaptation on person re-identification. In: Proceeding of the International Conference on Learning Representations, 2020

  15. Li J N, Zhang S L. Joint visual and temporal consistency for unsupervised domain adaptive person re-identification. In: Proceedings of the European Conference on Computer Vision, 2020. 483–499

  16. Ge Y X, Zhu F, Chen D P, et al. Self-paced contrastive learning with hybrid memory for domain adaptive object re-ID. In: Proceedings of Advances in Neural Information Processing Systems, 2020. 33: 11309–11321

    Google Scholar 

  17. Dai Y X, Liu J, Sun Y F, et al. IDM: an intermediate domain module for domain adaptive person re-ID. In: Proceedings of the IEEE International Conference on Computer Vision, 2021. 11864–11874

  18. Luo C C, Song C F, Zhang Z X. Generalizing person re-identification by camera-aware invariance learning and cross-domain mixup. In: Proceedings of the European Conference on Computer Vision, 2020. 224–241

  19. Dai Y X, Liu J, Bai Y, et al. Dual-refinement: joint label and feature refinement for unsupervised domain adaptive person re-identification. IEEE Trans Image Process, 2021, 30: 7815–7829

    Article  Google Scholar 

  20. Zheng K C, Lan C L, Zeng W J, et al. Exploiting sample uncertainty for domain adaptive person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2021. 3538–3546

  21. Lin Y T, Don X Y, Zheng L, et al. A bottom-up clustering approach to unsupervised person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2019. 8738–8745

  22. Wang M L, Lai B S, Huang J Q, et al. Camera-aware proxies for unsupervised person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2021. 1–4

  23. Wang Z D, Zhang J W, Zheng L, et al. CycAs: self-supervised cycle association for learning re-identifiable descriptions. In: Proceedings of the European Conference on Computer Vision, 2020. 72–88

  24. Xuan S Y, Zhang S L. Intra-inter camera similarity for unsupervised person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021. 11926–11935

  25. Wang D K, Zhang S L. Unsupervised person re-identification via multi-label classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2020. 10981–10990

  26. Yang F X, Zhong Z, Luo Z M, et al. Joint noise-tolerant learning and meta camera shift adaptation for unsupervised person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021. 4855–4864

  27. Lin Y T, Xie L X, Wu Y, et al. Unsupervised person re-identification via softened similarity learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2020. 3390–3399

  28. Wu J L, Yang Y, Liu H, et al. Unsupervised graph association for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, 2019. 8321–8330

  29. Ji Z L, Zou X L, Lin X H, et al. An attention-driven two-stage clustering method for unsupervised person re-identification. In: Proceedings of the European Conference on Computer Vision, 2020. 20–36

  30. Chen H, Lagadec B, Bremond F. ICE: inter-instance contrastive encoding for unsupervised person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, 2021. 14960–14969

  31. Dai Z Z, Wang G Y, Zhu S Y, et al. Cluster contrast for unsupervised person re-identification. 2021. ArXiv:2103.11568

  32. Zhang X, Ge Y X, Qiao Y, et al. 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, 2021. 3436–3445

  33. Chen H, Wang Y H, Lagadec B, et al. Joint generative and contrastive learning for unsupervised person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021. 2004–2013

  34. Wang J, Zhu X, Gong S, et al. Transferable joint attribute-identity deep learning for unsupervised person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018. 2275–2284

  35. Zheng K, Liu W, He L, et al. Group-aware label transfer for domain adaptive person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021. 5310–5319

  36. Yang Q, Yu H X, Wu A, et al. Patch-based discriminative feature learning for unsupervised person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019. 3633–3642

  37. Li X, Zhang H, Wang R, et al. Multiview clustering: a scalable and parameter-free bipartite graph fusion method. IEEE Trans Pattern Anal Mach Intell, 2020, 44: 330–344

    Article  Google Scholar 

  38. Ester M, Kriegel H P, Sander J, et al. A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, 1996. 226–231

  39. Zhong Z, Zheng L, Luo Z, et al. Learning to adapt invariance in memory for person re-identification. IEEE Trans Pattern Anal Mach Intell, 2020, 43: 2723–2738

    Google Scholar 

  40. Zhong Z, Zheng L, Cao D L, et al. Re-ranking person re-identification with k-reciprocal encoding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017. 1318–1327

  41. Kendall A, Gal Y. What uncertainties do we need in bayesian deep learning for computer vision? In: Proceedings of Advances in Neural Information Processing Systems, 2017. 30: 5574–5584

    Google Scholar 

  42. Zheng Z, Yang Y. Rectifying pseudo label learning via uncertainty estimation for domain adaptive semantic segmentation. Int J Comput Vis, 2021, 129: 1106–1120

    Article  Google Scholar 

  43. Zheng L, Shen L Y, Tian L, et al. Scalable person re-identification: a benchmark. In: Proceedings of the IEEE International Conference on Computer Vision, 2015. 1116–1124

  44. Zheng Z D, Zheng L, Yang Y. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: Proceedings of the IEEE International Conference on Computer Vision, 2017. 3754–3762

  45. Wei L H, Zhang S L, Gao W, et al. Person transfer GAN to bridge domain gap for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018. 79–88

  46. Zhong Z, Zheng L, Kang G, et al. Random erasing data augmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2020. 13001–13008

  47. van der Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res, 2008, 9: 2579–2605

    MATH  Google Scholar 

Download references

Acknowledgements

This work was supported by Natural Science Foundation of Beijing Municipality (Grant No. L192036).

Author information

Authors and Affiliations

  1. School of Information and Electronics, Beijing Institute of Technology, Beijing, 100081, China

    Yiyu Chen, Zheyi Fan, Shuni Chen & Yixuan Zhu

Authors
  1. Yiyu Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zheyi Fan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shuni Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yixuan Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zheyi Fan.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, Y., Fan, Z., Chen, S. et al. Improving pseudo-labeling with reliable inter-camera distance encouragement for unsupervised person re-identification. Sci. China Inf. Sci. 66, 152103 (2023). https://doi.org/10.1007/s11432-022-3628-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11432-022-3628-y

Keywords

Search

Navigation