Skip to main content
Springer Nature Link
Log in

Multi-memory Matching for Unsupervised Visible-Infrared Person Re-identification

  • Conference paper
  • First Online:
Computer Vision – ECCV 2024 (ECCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15076))

Included in the following conference series:

  • 678 Accesses

Abstract

Unsupervised visible-infrared person re-identification (USL-VI-ReID) is a promising yet highly challenging retrieval task. The key challenges in USL-VI-ReID are to accurately generate pseudo-labels and establish pseudo-label correspondences across modalities without relying on any prior annotations. Recently, clustered pseudo-label methods have gained more attention in USL-VI-ReID. However, most existing methods don’t fully exploit the intra-class nuances, as they simply utilize a single memory that represents an identity to establish cross-modality correspondences, resulting in noisy cross-modality correspondences. To address the problem, we propose a Multi-Memory Matching (MMM) framework for USL-VI-ReID. We first design a simple yet effective Cross-Modality Clustering (CMC) module to generate the pseudo-labels through clustering together both two modality samples. To associate cross-modality clustered pseudo-labels, we design a Multi-Memory Learning and Matching (MMLM) module, ensuring that optimization explicitly focuses on the nuances of individual perspectives and establishes reliable cross-modality correspondences. Finally, we design a Soft Cluster-level Alignment (SCA) loss to narrow the modality gap while mitigating the effect of noisy pseudo-labels through a soft many-to-many alignment strategy. Extensive experiments on the public SYSU-MM01 and RegDB datasets demonstrate the reliability of the established cross-modality correspondences and the effectiveness of MMM.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Arpit, D., et al.: A closer look at memorization in deep networks. In: ICML, pp. 233–242 (2017)

    Google Scholar 

  2. Chen, H., Lagadec, B., Brémond, F.: ICE: inter-instance contrastive encoding for unsupervised person re-identification. In: ICCV, pp. 14940–14949 (2021)

    Google Scholar 

  3. Chen, Y., Wan, L., Li, Z., Jing, Q., Sun, Z.: Neural feature search for RGB-infrared person re-identification. In: CVPR, pp. 587–597 (2021)

    Google Scholar 

  4. Chen, Z., Zhang, Z., Tan, X., Qu, Y., Xie, Y.: Unveiling the power of clip in unsupervised visible-infrared person re-identification. In: ACM MM, pp. 3667–3675 (2023)

    Google Scholar 

  5. Cheng, D., Huang, X., Wang, N., He, L., Li, Z., Gao, X.: Unsupervised visible-infrared person reid by collaborative learning with neighbor-guided label refinement. ArXiv:2305.12711 (2023)

  6. Cho, Y., Kim, W.J., Hong, S., Yoon, S.: Part-based pseudo label refinement for unsupervised person re-identification. In: CVPR, pp. 7298–7308 (2022)

    Google Scholar 

  7. Dai, Z., Wang, G., Yuan, W., Zhu, S., Tan, P.: Cluster contrast for unsupervised person re-identification. In: ACCV, pp. 319–337 (2022)

    Google Scholar 

  8. Ester, M., Kriegel, H., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: KDD, pp. 226–231 (1996)

    Google Scholar 

  9. Feng, J., Wu, A., Zheng, W.: Shape-erased feature learning for visible-infrared person re-identification. In: CVPR, pp. 22752–22761 (2023)

    Google Scholar 

  10. Fu, Y., Wei, Y., Wang, G., Zhou, Y., Shi, H., Huang, T.S.: Self-similarity grouping: A simple unsupervised cross domain adaptation approach for person re-identification. In: ICCV, pp. 6111–6120 (2019)

    Google Scholar 

  11. Ge, Y., Chen, D., Li, H.: Mutual mean-teaching: pseudo label refinery for unsupervised domain adaptation on person re-identification. In: ICLR (2020)

    Google Scholar 

  12. Ge, Y., Zhu, F., Chen, D., Zhao, R., Li, H.: Self-paced contrastive learning with hybrid memory for domain adaptive object re-id. In: NeurIPS (2020)

    Google Scholar 

  13. Gong, Y., Huang, L., Chen, L.: Person re-identification method based on color attack and joint defence. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 4312–4321. IEEE (2022)

    Google Scholar 

  14. Gong, Y., Zhong, Z., Luo, Z., Qu, Y., Ji, R., Jiang, M.: Cross-modality perturbation synergy attack for person re-identification. CoRR abs/2401.10090 (2024)

    Google Scholar 

  15. Gretton, A., Borgwardt, K.M., Rasch, M.J., Schölkopf, B., Smola, A.: A kernel two-sample test. J. Mach. Learn. Res. 13(1), 723–773 (2012)

    MathSciNet  Google Scholar 

  16. He, L., Wang, N., Zhang, S., Wang, Z., Gao, X., et al.: Efficient bilateral cross-modality cluster matching for unsupervised visible-infrared person reid. ArXiv:2305.12673 (2023)

  17. Hubert, L., Arabie, P.: Comparing partitions. J. Classificat. 2, 193–218 (1985)

    Article  Google Scholar 

  18. Shi, J., et al.: Progressive contrastive learning with multi-prototype for unsupervised visible-infrared person re-identification. arXiv:2402.19026 (2024)

  19. Kim, M., Kim, S., Park, J., Park, S., Sohn, K.: Partmix: regularization strategy to learn part discovery for visible-infrared person re-identification. In: CVPR, pp. 18621–18632 (2023)

    Google Scholar 

  20. Li, H., Ye, M., Zhang, M., Du, B.: All in one framework for multimodal re-identification in the wild. In: CVPR. pp. 17459–17469 (2024)

    Google Scholar 

  21. Liang, W., Wang, G., Lai, J., Xie, X.: Homogeneous-to-heterogeneous: Unsupervised learning for RGB-infrared person re-identification. IEEE Trans. Image Process. 30, 6392–6407 (2021)

    Article  MathSciNet  Google Scholar 

  22. Lin, L., Liu, H., Liang, J., Li, Z., Feng, J., Han, H.: Consensus-agent deep reinforcement learning for face aging. IEEE Trans. Image Process. (2024)

    Google Scholar 

  23. Lin, L., Wang, T., Liu, H., Zhu, C., Chen, J.: Toward quantifiable face age transformation under attribute unbias. IEEE Trans. Circuits Syst. Video Technol. (2024)

    Google Scholar 

  24. Lin, Y., Xie, L., Wu, Y., Yan, C., Tian, Q.: Unsupervised person re-identification via softened similarity learning. In: CVPR, pp. 3387–3396 (2020)

    Google Scholar 

  25. Nguyen, D.T., Hong, H.G., Kim, K., Park, K.R.: Person recognition system based on a combination of body images from visible light and thermal cameras. Sensors 17(3), 605 (2017)

    Article  Google Scholar 

  26. Pang, Z., Wang, C., Zhao, L., Liu, Y., Sharma, G.: Cross-modality hierarchical clustering and refinement for unsupervised visible-infrared person re-identification. IEEE Trans. Circuits Syst. Video Technol. 1–1 (2023)

    Google Scholar 

  27. Pang, Z., Zhao, L., Liu, Q., Wang, C.: Camera invariant feature learning for unsupervised person re-identification. IEEE Trans. Multimedia 25, 6171–6182 (2022)

    Article  Google Scholar 

  28. Park, H., Lee, S., Lee, J., Ham, B.: Learning by aligning: visible-infrared person re-identification using cross-modal correspondences. In: ICCV, pp. 12026–12035 (2021)

    Google Scholar 

  29. Shi, J., Yin, X., Zhang, D., Qu, Y.: Visible embraces infrared: cross-modality person re-identification with single-modality supervision. In: 2023 China Automation Congress (CAC), pp. 4781–4787. IEEE (2023)

    Google Scholar 

  30. Shi, J., et al.: Dual pseudo-labels interactive self-training for semi-supervised visible-infrared person re-identification. In: ICCV, pp. 11218–11228 (2023)

    Google Scholar 

  31. Sun, H., et al.: Not all pixels are matched: dense contrastive learning for cross-modality person re-identification. In: ACM MM, pp. 5333–5341 (2022)

    Google Scholar 

  32. Tan, L., Dai, P., Ji, R., Wu, Y.: Dynamic prototype mask for occluded person re-identification. In: ACM MM, pp. 531–540 (2022)

    Google Scholar 

  33. Tan, L., Xia, J., Liu, W., Dai, P., Wu, Y., Cao, L.: Occluded person re-identification via saliency-guided patch transfer. In: AAAI, vol. 38, pp. 5070–5078 (2024)

    Google Scholar 

  34. Tang, Y., et al.: Align before search: aligning ads image to text for accurate cross-modal sponsored search (2023)

    Google Scholar 

  35. Tang, Y., et al.: Context-i2w: mapping images to context-dependent words for accurate zero-shot composed image retrieval. In: AAAI, vol. 38, pp. 5180–5188 (2024)

    Google Scholar 

  36. Wang, D., Zhang, S.: Unsupervised person re-identification via multi-label classification. In: CVPR, pp. 10978–10987 (2020)

    Google Scholar 

  37. Wang, G., et al.: Cross-modality paired-images generation and augmentation for RGB-infrared person re-identification. Neural Netw. 128, 294–304 (2020)

    Article  Google Scholar 

  38. Wang, J., et al.: Optimal transport for label-efficient visible-infrared person re-identification. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13684, pp. 93–109. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20053-3_6

    Chapter  Google Scholar 

  39. Wang, Y., Liu, X., Zhang, P., Lu, H., Tu, Z., Lu, H.: Top-reid: multi-spectral object re-identification with token permutation. In: AAAI, vol. 38, pp. 5758–5766 (2024)

    Google Scholar 

  40. Wei, Z., Yang, X., Wang, N., Gao, X.: Syncretic modality collaborative learning for visible infrared person re-identification. In: ICCV, pp. 225–234 (2021)

    Google Scholar 

  41. Wu, A., Zheng, W., Yu, H., Gong, S., Lai, J.: RGB-infrared cross-modality person re-identification. In: ICCV, pp. 5390–5399 (2017)

    Google Scholar 

  42. Wu, Y., et al.: Multi-centroid representation network for domain adaptive person re-id. In: AAAI, pp. 2750–2758 (2022)

    Google Scholar 

  43. Wu, Z., Ye, M.: Unsupervised visible-infrared person re-identification via progressive graph matching and alternate learning. In: CVPR, pp. 9548–9558 (2023)

    Google Scholar 

  44. Yang, B., Chen, J., Ma, X., Ye, M.: Translation, association and augmentation: learning cross-modality re-identification from single-modality annotation. IEEE Trans. Image Process. 32, 5099–5113 (2023)

    Article  Google Scholar 

  45. Yang, B., Chen, J., Ye, M.: Towards grand unified representation learning for unsupervised visible-infrared person re-identification. In: ICCV, pp. 11069–11079 (2023)

    Google Scholar 

  46. Yang, B., Chen, J., Ye, M.: Shallow-deep collaborative learning for unsupervised visible-infrared person re-identification. In: CVPR, pp. 16870–16879 (2024)

    Google Scholar 

  47. Yang, B., Ye, M., Chen, J., Wu, Z.: Augmented dual-contrastive aggregation learning for unsupervised visible-infrared person re-identification. In: ACM MM, pp. 2843–2851 (2022)

    Google Scholar 

  48. Yang, M., Huang, Z., Hu, P., Li, T., Lv, J., Peng, X.: Learning with twin noisy labels for visible-infrared person re-identification. In: CVPR, pp. 14288–14297 (2022)

    Google Scholar 

  49. Yang, M., Huang, Z., Peng, X.: Robust object re-identification with coupled noisy labels. IJCV 1–19 (2024)

    Google Scholar 

  50. Ye, M., Ruan, W., Du, B., Shou, M.Z.: Channel augmented joint learning for visible-infrared recognition. In: ICCV, pp. 13547–13556 (2021)

    Google Scholar 

  51. Ye, M., Shen, J., Lin, G., Xiang, T., Shao, L., Hoi, S.C.H.: Deep learning for person re-identification: a survey and outlook. IEEE Trans. Pattern Anal. Mach. Intell. 2872–2893 (2022)

    Google Scholar 

  52. Ye, M., Wang, Z., Lan, X., Yuen, P.C.: Visible thermal person re-identification via dual-constrained top-ranking. In: IJCAI, pp. 1092–1099 (2018)

    Google Scholar 

  53. Yin, X., et al.: Robust pseudo-label learning with neighbor relation for unsupervised visible-infrared person re-identification. CoRR abs/2405.05613 (2024)

    Google Scholar 

  54. Zhai, Y., Ye, Q., Lu, S., Jia, M., Ji, R., Tian, Y.: Multiple expert brainstorming for domain adaptive person re-identification. In: ECCV, vol. 12352, pp. 594–611 (2020)

    Google Scholar 

  55. Zhang, G., Zhang, H., Lin, W., Chandran, A.K., Jing, X.: Camera contrast learning for unsupervised person re-identification. IEEE Trans. Circuits Syst. Video Technol. 33(8), 4096–4107 (2023)

    Article  Google Scholar 

  56. Zhang, P., Wang, Y., Liu, Y., Tu, Z., Lu, H.: Magic tokens: Select diverse tokens for multi-modal object re-identification. In: CVPR, pp. 17117–17126 (2024)

    Google Scholar 

  57. Zhang, Q., Lai, C., Liu, J., Huang, N., Han, J.: FMCNet: feature-level modality compensation for visible-infrared person re-identification. In: CVPR, pp. 7339–7348 (2022)

    Google Scholar 

  58. Zhang, Y., Wang, H.: Diverse embedding expansion network and low-light cross-modality benchmark for visible-infrared person re-identification. In: CVPR, pp. 2153–2162 (2023)

    Google Scholar 

  59. Zhang, Y., Yan, Y., Lu, Y., Wang, H.: Towards a unified middle modality learning for visible-infrared person re-identification. In: ACM MM, pp. 788–796 (2021)

    Google Scholar 

  60. Zhang, Z., Xie, Y., Li, D., Zhang, W., Tian, Q.: Learning to align via wasserstein for person re-identification. IEEE Trans. Image Process. 29, 7104–7116 (2020)

    Article  Google Scholar 

  61. Zou, C., Chen, Z., Cui, Z., Liu, Y., Zhang, C.: Discrepant and multi-instance proxies for unsupervised person re-identification. In: ICCV, pp. 11058–11068 (2023)

    Google Scholar 

  62. Zuo, J., et al..: Ufinebench: Towards text-based person retrieval with ultra-fine granularity. In: CVPR, pp. 22010–22019 (2024)

    Google Scholar 

Download references

Acknowledgments

This work is supported by the National Natural Science Foundation of China (No. 62176224, 62222602, 62106075, 62176092, 62306165), Natural Science Foundation of Shanghai (23ZR1420400), Natural Science Foundation of Chongqing (CSTB2023NSCQ-JQX0007), China Postdoctoral Science Foundation (No. 2023M731957), CCF-Lenovo Blue Ocean Research Fund.

Author information

Authors and Affiliations

  1. Institute of Artificial Intelligence, Xiamen University, Xiamen, China

    Jiangming Shi, Yeyun Chen & Yanyun Qu

  2. School of Informatics, Xiamen University, Xiamen, China

    Xiangbo Yin & Yanyun Qu

  3. Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China

    Yachao Zhang

  4. School of Computer Science and Technology, East China Normal University, Shanghai, China

    Zhizhong Zhang & Yuan Xie

  5. Shanghai Key Laboratory of Computer Software Evaluating and Testing, Shanghai, China

    Zhizhong Zhang

Authors
  1. Jiangming Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiangbo Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yeyun Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yachao Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhizhong Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yuan Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Yanyun Qu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Yuan Xie or Yanyun Qu .

Editor information

Editors and Affiliations

  1. University of Birmingham, Birmingham, UK

    Aleš Leonardis

  2. University of Trento, Trento, Italy

    Elisa Ricci

  3. Technical University of Darmstadt, Darmstadt, Germany

    Stefan Roth

  4. Princeton University, Princeton, NJ, USA

    Olga Russakovsky

  5. Czech Technical University in Prague, Prague, Czech Republic

    Torsten Sattler

  6. École des Ponts ParisTech, Marne-la-Vallée, France

    Gül Varol

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 116 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Shi, J. et al. (2025). Multi-memory Matching for Unsupervised Visible-Infrared Person Re-identification. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15076. Springer, Cham. https://doi.org/10.1007/978-3-031-72649-1_26

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-72649-1_26

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-72648-4

  • Online ISBN: 978-3-031-72649-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics