Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

SiCL: Silhouette-Driven Contrastive Learning for Unsupervised Person Re-Identification with Clothes Change (2305.13600v2)

Published 23 May 2023 in cs.CV

Abstract: In this paper, we address a highly challenging yet critical task: unsupervised long-term person re-identification with clothes change. Existing unsupervised person re-id methods are mainly designed for short-term scenarios and usually rely on RGB cues so that fail to perceive feature patterns that are independent of the clothes. To crack this bottleneck, we propose a silhouette-driven contrastive learning (SiCL) method, which is designed to learn cross-clothes invariance by integrating both the RGB cues and the silhouette information within a contrastive learning framework. To our knowledge, this is the first tailor-made framework for unsupervised long-term clothes change \reid{}, with superior performance on six benchmark datasets. We conduct extensive experiments to evaluate our proposed SiCL compared to the state-of-the-art unsupervised person reid methods across all the representative datasets. Experimental results demonstrate that our proposed SiCL significantly outperforms other unsupervised re-id methods.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (38)
  1. Ice: Inter-instance contrastive encoding for unsupervised person re-identification. In ICCV, pages 14960–14969, 2021a.
  2. Learning 3d shape feature for texture-insensitive person re-identification. In CVPR, pages 8146–8155, 2021b.
  3. Part-based pseudo label refinement for unsupervised person re-identification. In CVPR, pages 7308–7318, 2022.
  4. Cluster contrast for unsupervised person re-identification. arXiv preprint arXiv:2103.11568, 2021.
  5. Cluster contrast for unsupervised person re-identification. In ACCV, pages 1142–1160, 2022.
  6. A density-based algorithm for discovering clusters in large spatial databases with noise. In SIGKDD, 1996.
  7. Fd-gan: Pose-guided feature distilling gan for robust person re-identification. In NeurIPS, 2018.
  8. Self-paced contrastive learning with hybrid memory for domain adaptive object re-id. In NeurIPS, 2020.
  9. Clothes-changing person re-identification with rgb modality only. In CVPR, pages 1060–1069, 2022.
  10. Deep residual learning for image recognition. In CVPR, 2016.
  11. Fine-grained shape-appearance mutual learning for cloth-changing person re-identification. In CVPR, 2021a.
  12. Fine-grained shape-appearance mutual learning for cloth-changing person re-identification. In CVPR, pages 10513–10522, 2021b.
  13. Interaction-and-aggregation network for person re-identification. In CVPR, pages 9317–9326, 2019.
  14. Celebrities-reid: A benchmark for clothes variation in long-term person re-identification. In IJCNN, pages 1–8. IEEE, 2019a.
  15. Beyond scalar neuron: Adopting vector-neuron capsules for long-term person re-identification. TCSVT, 30(10):3459–3471, 2019b.
  16. Clothing status awareness for long-term person re-identification. In ICCV, pages 11895–11904, 2021.
  17. Cloth-changing person re-identification from a single image with gait prediction and regularization. In CVPR, pages 14278–14287, 2022.
  18. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations, 2015.
  19. Imagenet classification with deep convolutional neural networks. In NeurIPS, 2012.
  20. Cluster-guided asymmetric contrastive learning for unsupervised person re-identification. TIP, 2022.
  21. Unsupervised person re-identification by deep learning tracklet association. In ECCV, 2018a.
  22. The devil in the tail: Cluster consolidation plus cluster adaptive balancing loss for unsupervised person re-identification. PR, 129:108763, 2022.
  23. Self-correction for human parsing. TPAMI, 2020.
  24. Harmonious attention network for person re-identification. In CVPR, pages 2285–2294, 2018b.
  25. Unsupervised cross-dataset transfer learning for person re-identification. In CVPR, 2016.
  26. Long-term cloth-changing person re-identification. In ACCV, 2020.
  27. Person re-identification with a cloth-changing aware transformer. In 2022 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE, 2022.
  28. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In ECCV, pages 480–496, 2018.
  29. When person re-identification meets changing clothes. In CVPRW, 2020.
  30. Transferable joint attribute-identity deep learning for unsupervised person re-identification. In CVPR, 2018.
  31. A benchmark for clothes variation in person re-identification. IJIS, 2020.
  32. Deepchange: A long-term person re-identification benchmark with clothes change. In Proceedings of the IEEE international conference on computer vision (ICCV), 2023.
  33. Person re-identification by contour sketch under moderate clothing change. TPAMI, 2019a.
  34. Person re-identification by contour sketch under moderate clothing change. TPAMI, 2019b.
  35. Deep learning for person re-identification: A survey and outlook. arXiv preprint arXiv:2001.04193, 2020.
  36. Relation-aware global attention for person re-identification. In CVPR, pages 3186–3195, 2020.
  37. Person re-identification by saliency learning. TPAMI, 2016.
  38. Person re-identification: Past, present and future. arXiv preprint arXiv:1610.02984, 2016.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Mingkun Li (6 papers)
  2. Peng Xu (357 papers)
  3. Chun-Guang Li (22 papers)
  4. Jun Guo (130 papers)
Citations (1)
View on Semantic Scholar