Papers
Topics
Authors
Recent
2000 character limit reached

Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification (2402.19026v3)

Published 29 Feb 2024 in cs.CV

Abstract: Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match specified people in infrared images to visible images without annotations, and vice versa. USVI-ReID is a challenging yet under-explored task. Most existing methods address the USVI-ReID using cluster-based contrastive learning, which simply employs the cluster center as a representation of a person. However, the cluster center primarily focuses on commonality, overlooking divergence and variety. To address the problem, we propose a Progressive Contrastive Learning with Hard and Dynamic Prototypes method for USVI-ReID. In brief, we generate the hard prototype by selecting the sample with the maximum distance from the cluster center. We theoretically show that the hard prototype is used in the contrastive loss to emphasize divergence. Additionally, instead of rigidly aligning query images to a specific prototype, we generate the dynamic prototype by randomly picking samples within a cluster. The dynamic prototype is used to encourage the variety. Finally, we introduce a progressive learning strategy to gradually shift the model's attention towards divergence and variety, avoiding cluster deterioration. Extensive experiments conducted on the publicly available SYSU-MM01 and RegDB datasets validate the effectiveness of the proposed method.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. Visible-infrared person re-identification using privileged intermediate information. In ECCV, pages 720–737, 2022.
  2. Neural feature search for rgb-infrared person re-identification. In CVPR, pages 587–597, 2021.
  3. Unveiling the power of clip in unsupervised visible-infrared person re-identification. In ACM MM, pages 3667–3675, 2023.
  4. Unsupervised visible-infrared person reid by collaborative learning with neighbor-guided label refinement. 2023.
  5. Part-based pseudo label refinement for unsupervised person re-identification. In CVPR, pages 7298–7308, 2022.
  6. Cluster contrast for unsupervised person re-identification. In ACCV, pages 319–337, 2022.
  7. A density-based algorithm for discovering clusters in large spatial databases with noise. In KDD, pages 226–231, 1996.
  8. Visible-infrared person re-identification via semantic alignment and affinity inference. In ICCV, pages 11270–11279, 2023.
  9. Shape-erased feature learning for visible-infrared person re-identification. In CVPR, pages 22752–22761, 2023.
  10. Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification. In ICLR, 2020.
  11. Self-paced contrastive learning with hybrid memory for domain adaptive object re-id. In NeurIPS, 2020.
  12. Person re-identification method based on color attack and joint defence. In CVPR Workshops, pages 4312–4321, 2022.
  13. Cross-modality perturbation synergy attack for person re-identification. arXiv preprint arXiv:2401.10090, 2024.
  14. Momentum contrast for unsupervised visual representation learning. In ICCV, pages 9729–9738, 2020.
  15. Efficient bilateral cross-modality cluster matching for unsupervised visible-infrared person reid. 2023.
  16. Modality-adaptive mixup and invariant decomposition for rgb-infrared person re-identification. In AAAI, pages 1034–1042, 2022.
  17. Partmix: Regularization strategy to learn part discovery for visible-infrared person re-identification. In CVPR, pages 18621–18632, 2023.
  18. Infrared-visible cross-modal person re-identification with an X modality. In AAAI, pages 4610–4617, 2020.
  19. Homogeneous-to-heterogeneous: Unsupervised learning for rgb-infrared person re-identification. IEEE Trans. Image Process., 30:6392–6407, 2021.
  20. Learning memory-augmented unidirectional metrics for cross-modality person re-identification. In CVPR, pages 19344–19353, 2022.
  21. Learning progressive modality-shared transformers for effective visible-infrared person re-identification. In AAAI, pages 1835–1843, 2023.
  22. Person recognition system based on a combination of body images from visible light and thermal cameras. Sensors, 17(3):605, 2017.
  23. Fully unsupervised person re-identification via selective contrastive learning. TOMM, 18(2):1–15, 2022.
  24. Learning by aligning: Visible-infrared person re-identification using cross-modal correspondences. In ICCV, pages 12026–12035, 2021.
  25. Dual pseudo-labels interactive self-training for semi-supervised visible-infrared person re-identification. In ICCV, pages 11218–11228, 2023.
  26. Multi-memory matching for unsupervised visible-infrared person re-identification. ArXiv, 2024.
  27. Not all pixels are matched: Dense contrastive learning for cross-modality person re-identification. In ACM MM, pages 5333–5341, 2022.
  28. Rgb-infrared cross-modality person re-identification via joint pixel and feature alignment. In ICCV, pages 3622–3631, 2019.
  29. Cross-modality paired-images generation and augmentation for rgb-infrared person re-identification. Neural Networks, 128:294–304, 2020.
  30. Optimal transport for label-efficient visible-infrared person re-identification. In ECCV, pages 93–109, 2022.
  31. Syncretic modality collaborative learning for visible infrared person re-identification. In ICCV, pages 225–234, 2021.
  32. Unsupervised visible-infrared person re-identification via progressive graph matching and alternate learning. In CVPR, pages 9548–9558, 2023.
  33. Rgb-infrared cross-modality person re-identification. In ICCV, pages 5390–5399, 2017.
  34. Discover cross-modality nuances for visible-infrared person re-identification. In CVPR, pages 4330–4339, 2021.
  35. Multi-centroid representation network for domain adaptive person re-id. In AAAI, pages 2750–2758, 2022.
  36. Learning concordant attention via target-aware alignment for visible-infrared person re-identification. In ICCV, pages 11122–11131, 2023.
  37. Partially view-aligned representation learning with noise-robust contrastive loss. In CVPR, pages 1134–1143, 2021.
  38. Augmented dual-contrastive aggregation learning for unsupervised visible-infrared person re-identification. In ACM MM, pages 2843–2851, 2022.
  39. Learning with twin noisy labels for visible-infrared person re-identification. In CVPR, pages 14288–14297, 2022.
  40. Dual consistency-constrained learning for unsupervised visible-infrared person re-identification. IEEE Transactions on Information Forensics and Security, 2023.
  41. Translation, association and augmentation: Learning cross-modality re-identification from single-modality annotation. IEEE Transactions on Image Processing, 32:5099–5113, 2023.
  42. Towards grand unified representation learning for unsupervised visible-infrared person re-identification. In ICCV, pages 11069–11079, 2023.
  43. Robust multi-view clustering with incomplete information. IEEE Trans. Pattern Anal. Mach. Intell., 45(1):1055–1069, 2023.
  44. Robust object re-identification with coupled noisy labels. International Journal of Computer Vision, pages 1–19, 2024.
  45. Visible thermal person re-identification via dual-constrained top-ranking. In IJCAI, pages 1092–1099, 2018.
  46. Dynamic dual-attentive aggregation learning for visible-infrared person re-identification. In ECCV, pages 229–247, 2020.
  47. Channel augmented joint learning for visible-infrared recognition. In ICCV, pages 13547–13556, 2021.
  48. Deep learning for person re-identification: A survey and outlook. IEEE Trans. Pattern Anal. Mach. Intell., pages 2872–2893, 2022.
  49. Modality unifying network for visible-infrared person re-identification. In ICCV, pages 11185–11195, 2023.
  50. Diverse embedding expansion network and low-light cross-modality benchmark for visible-infrared person re-identification. In CVPR, pages 2153–2162, 2023.
  51. Towards a unified middle modality learning for visible-infrared person re-identification. In ACM MM, pages 788–796, 2021.
  52. Fmcnet: Feature-level modality compensation for visible-infrared person re-identification. In CVPR, pages 7339–7348, 2022.
  53. Protohpe: Prototype-guided high-frequency patch enhancement for visible-infrared person re-identification. In MM, pages 944–954, 2023.
  54. Camera contrast learning for unsupervised person re-identification. IEEE Trans. Circuits Syst. Video Technol., 33(8):4096–4107, 2023.
  55. Frequency domain nuances mining for visible-infrared person re-identification. arXiv preprint arXiv:2401.02162, 2024.
  56. Discrepant and multi-instance proxies for unsupervised person re-identification. In ICCV, pages 11058–11068, 2023.
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now

Whiteboard

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up