Papers
Topics
Authors
Recent
Search
2000 character limit reached

Adaptive Intra-Class Variation Contrastive Learning for Unsupervised Person Re-Identification

Published 6 Apr 2024 in cs.CV and cs.AI | (2404.04665v1)

Abstract: The memory dictionary-based contrastive learning method has achieved remarkable results in the field of unsupervised person Re-ID. However, The method of updating memory based on all samples does not fully utilize the hardest sample to improve the generalization ability of the model, and the method based on hardest sample mining will inevitably introduce false-positive samples that are incorrectly clustered in the early stages of the model. Clustering-based methods usually discard a significant number of outliers, leading to the loss of valuable information. In order to address the issues mentioned before, we propose an adaptive intra-class variation contrastive learning algorithm for unsupervised Re-ID, called AdaInCV. And the algorithm quantitatively evaluates the learning ability of the model for each class by considering the intra-class variations after clustering, which helps in selecting appropriate samples during the training process of the model. To be more specific, two new strategies are proposed: Adaptive Sample Mining (AdaSaM) and Adaptive Outlier Filter (AdaOF). The first one gradually creates more reliable clusters to dynamically refine the memory, while the second can identify and filter out valuable outliers as negative samples.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Scalable person re-identification on supervised smoothed manifold. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2530–2539.
  2. Unsupervised multi-source domain adaptation for person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 12914–12923.
  3. Yoshua Bengio et al. 2009. Learning deep architectures for AI. Foundations and trends® in Machine Learning 2, 1 (2009), 1–127.
  4. Deep credible metric learning for unsupervised domain adaptation person re-identification. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VIII 16. Springer, 643–659.
  5. Enhancing diversity in teacher-student networks via asymmetric branches for unsupervised person re-identification. In Proceedings of the IEEE/CVF winter conference on applications of computer vision. 1–10.
  6. Ice: Inter-instance contrastive encoding for unsupervised person re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 14960–14969.
  7. Joint generative and contrastive learning for unsupervised person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2004–2013.
  8. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597–1607.
  9. Hybrid dynamic contrast and probability distillation for unsupervised person re-id. IEEE Transactions on Image Processing 31 (2022), 3334–3346.
  10. Part-based pseudo label refinement for unsupervised person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7308–7318.
  11. Cluster contrast for unsupervised person re-identification. In Proceedings of the Asian Conference on Computer Vision. 1142–1160.
  12. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. Ieee, 248–255.
  13. A density-based algorithm for discovering clusters in large spatial databases with noise. In kdd, Vol. 96. 226–231.
  14. Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification. arXiv preprint arXiv:2001.01526 (2020).
  15. Self-paced contrastive learning with hybrid memory for domain adaptive object re-id. Advances in neural information processing systems 33 (2020), 11309–11321.
  16. Evaluating appearance models for recognition, reacquisition, and tracking. In Proc. IEEE international workshop on performance evaluation for tracking and surveillance (PETS), Vol. 3. 1–7.
  17. Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems 33 (2020), 21271–21284.
  18. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 9729–9738.
  19. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778.
  20. Hard-sample guided hybrid contrast learning for unsupervised person re-identification. In 2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC). IEEE, 91–95.
  21. Self-paced learning for latent variable models. Advances in neural information processing systems 23 (2010).
  22. Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 11453–11462.
  23. Jianing Li and Shiliang Zhang. 2020. Joint visual and temporal consistency for unsupervised domain adaptive person re-identification. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXIV 16. Springer, 483–499.
  24. A bottom-up clustering approach to unsupervised person re-identification. In Proceedings of the AAAI conference on artificial intelligence, Vol. 33. 8738–8745.
  25. Unsupervised person re-identification via softened similarity learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 3390–3399.
  26. Dual-Uncertainty Guided Curriculum Learning and Part-Aware Feature Refinement for Domain Adaptive Person Re-Identification. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1–5.
  27. Deep learning-based person re-identification methods: A survey and outlook of recent works. Image and Vision Computing 119 (2022), 104394.
  28. Fine-tuning CNN image retrieval with no human annotation. IEEE transactions on pattern analysis and machine intelligence 41, 7 (2018), 1655–1668.
  29. From baby steps to leapfrog: How “less is more” in unsupervised dependency parsing. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics. 751–759.
  30. Laurens Van Der Maaten. 2014. Accelerating t-SNE using tree-based algorithms. The journal of machine learning research 15, 1 (2014), 3221–3245.
  31. Dongkai Wang and Shiliang Zhang. 2020. Unsupervised person re-identification via multi-label classification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 10981–10990.
  32. Camera-aware proxies for unsupervised person re-identification. In Proceedings of the AAAI conference on artificial intelligence, Vol. 35. 2764–2772.
  33. A survey on curriculum learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 9 (2021), 4555–4576.
  34. Cycas: Self-supervised cycle association for learning re-identifiable descriptions. In Proceedings of the European conference on computer vision (ECCV). 72–88.
  35. Person transfer gan to bridge domain gap for person re-identification. In Proceedings of the IEEE conference on computer vision and pattern recognition. 79–88.
  36. Multi-centroid representation network for domain adaptive person re-id. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 2750–2758.
  37. Hierarchical clustering with hard-batch triplet loss for person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 13657–13665.
  38. Ad-cluster: Augmented discriminative clustering for domain adaptive person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 9021–9030.
  39. Unsupervised domain adaptation for person re-identification via heterogeneous graph alignment. In Proceedings of the AAAI conference on artificial intelligence, Vol. 35. 3360–3368.
  40. Implicit sample extension for unsupervised person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7369–7378.
  41. Exploiting sample uncertainty for domain adaptive person re-identification. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 3538–3546.
  42. Group-aware label transfer for domain adaptive person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 5310–5319.
  43. Scalable person re-identification: A benchmark. In Proceedings of the IEEE international conference on computer vision. 1116–1124.
  44. Re-ranking person re-identification with k-reciprocal encoding. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1318–1327.
  45. Adaptive Sparse Pairwise Loss for Object Re-Identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 19691–19701.
  46. Joint disentangling and adaptation for cross-domain person re-identification. In Proceedings of the European conference on computer vision (ECCV). Springer, 87–104.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

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

Generate Now

Continue Learning

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

Generate Now

Collections

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

Sign Up