Papers
Topics
Authors
Recent
Search
2000 character limit reached

ReMix: Training Generalized Person Re-identification on a Mixture of Data

Published 29 Oct 2024 in cs.CV, cs.AI, and cs.LG | (2410.21938v1)

Abstract: Modern person re-identification (Re-ID) methods have a weak generalization ability and experience a major accuracy drop when capturing environments change. This is because existing multi-camera Re-ID datasets are limited in size and diversity, since such data is difficult to obtain. At the same time, enormous volumes of unlabeled single-camera records are available. Such data can be easily collected, and therefore, it is more diverse. Currently, single-camera data is used only for self-supervised pre-training of Re-ID methods. However, the diversity of single-camera data is suppressed by fine-tuning on limited multi-camera data after pre-training. In this paper, we propose ReMix, a generalized Re-ID method jointly trained on a mixture of limited labeled multi-camera and large unlabeled single-camera data. Effective training of our method is achieved through a novel data sampling strategy and new loss functions that are adapted for joint use with both types of data. Experiments show that ReMix has a high generalization ability and outperforms state-of-the-art methods in generalizable person Re-ID. To the best of our knowledge, this is the first work that explores joint training on a mixture of multi-camera and single-camera data in person Re-ID.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (61)
  1. Evaluating multiple object tracking performance: the clear mot metrics. EURASIP Journal on Image and Video Processing, 2008:1–10, 2008.
  2. Ice: Inter-instance contrastive encoding for unsupervised person re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 14960–14969, 2021.
  3. A simple framework for contrastive learning of visual representations. In International conference on machine learning, pages 1597–1607. PMLR, 2020.
  4. Beyond appearance: a semantic controllable self-supervised learning framework for human-centric visual tasks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15050–15061, 2023.
  5. Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297, 2020.
  6. Meta batch-instance normalization for generalizable person re-identification. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, pages 3425–3435, 2021.
  7. Generalizable person re-identification with relevance-aware mixture of experts. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16145–16154, 2021.
  8. With a little help from my friends: Nearest-neighbor contrastive learning of visual representations. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9588–9597, 2021.
  9. A density-based algorithm for discovering clusters in large spatial databases with noise. In kdd, volume 96, pages 226–231, 1996.
  10. Unsupervised pre-training for person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14750–14759, 2021.
  11. Unsupervised representation learning by predicting image rotations. arXiv preprint arXiv:1803.07728, 2018.
  12. Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16000–16009, 2022.
  13. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  14. Transreid: Transformer-based object re-identification. In Proceedings of the IEEE/CVF international conference on computer vision, pages 15013–15022, 2021.
  15. Frustratingly easy person re-identification: Generalizing person re-id in practice. arXiv preprint arXiv:1905.03422, 2019.
  16. Learning disentangled representation implicitly via transformer for occluded person re-identification. IEEE Transactions on Multimedia, 25:1294–1305, 2022.
  17. Dynamically transformed instance normalization network for generalizable person re-identification. In European Conference on Computer Vision, pages 285–301. Springer, 2022.
  18. Style normalization and restitution for generalizable person re-identification. In proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 3143–3152, 2020.
  19. L Leal-Taixe. Motchallenge 2015: Towards a benchmark for multi-target tracking. arXiv preprint arXiv:1504.01942, 2015.
  20. Combined depth space based architecture search for person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6729–6738, 2021.
  21. Clip-reid: exploiting vision-language model for image re-identification without concrete text labels. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 1405–1413, 2023.
  22. Deepreid: Deep filter pairing neural network for person re-identification. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 152–159, 2014.
  23. Learning to associate: Hybridboosted multi-target tracker for crowded scene. In 2009 IEEE conference on computer vision and pattern recognition, pages 2953–2960. IEEE, 2009.
  24. Interpretable and generalizable person re-identification with query-adaptive convolution and temporal lifting. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XI 16, pages 456–474. Springer, 2020.
  25. Transmatcher: Deep image matching through transformers for generalizable person re-identification. Advances in Neural Information Processing Systems, 34:1992–2003, 2021.
  26. Graph sampling based deep metric learning for generalizable person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7359–7368, 2022.
  27. Approaches to improve the quality of person re-identification for practical use. Sensors, 23(17):7382, 2023.
  28. Anton Milan. Mot16: A benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831, 2016.
  29. Part-aware transformer for generalizable person re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 11280–11289, 2023.
  30. Meta distribution alignment for generalizable person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2487–2496, 2022.
  31. Flipreid: closing the gap between training and inference in person re-identification. In 2021 9th European Workshop on Visual Information Processing (EUVIP), pages 1–6. IEEE, 2021.
  32. Unsupervised learning of visual representations by solving jigsaw puzzles. In European conference on computer vision, pages 69–84. Springer, 2016.
  33. Two at once: Enhancing learning and generalization capacities via ibn-net. In Proceedings of the European Conference on Computer Vision (ECCV), pages 464–479, 2018.
  34. A novel mix-normalization method for generalizable multi-source person re-identification. IEEE Transactions on Multimedia, 2022.
  35. Counterfactual attention learning for fine-grained visual categorization and re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1025–1034, 2021.
  36. Performance measures and a data set for multi-target, multi-camera tracking. In European conference on computer vision, pages 17–35. Springer, 2016.
  37. Person re-identification with deep similarity-guided graph neural network. In Proceedings of the European conference on computer vision (ECCV), pages 486–504, 2018.
  38. Part-aligned bilinear representations for person re-identification. In Proceedings of the European conference on computer vision (ECCV), pages 402–419, 2018.
  39. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In Proceedings of the European conference on computer vision (ECCV), pages 480–496, 2018.
  40. Dynamic prototype mask for occluded person re-identification. In Proceedings of the 30th ACM International Conference on Multimedia, pages 531–540, 2022.
  41. Style interleaved learning for generalizable person re-identification. IEEE Transactions on Multimedia, 2023.
  42. Learning discriminative features with multiple granularities for person re-identification. In Proceedings of the 26th ACM international conference on Multimedia, pages 274–282, 2018.
  43. Nformer: Robust person re-identification with neighbor transformer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7297–7307, 2022.
  44. Camera-aware proxies for unsupervised person re-identification. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 2764–2772, 2021.
  45. Ltreid: Factorizable feature generation with independent components for long-tailed person re-identification. IEEE Transactions on Multimedia, 25:4610–4622, 2022.
  46. Surpassing real-world source training data: Random 3d characters for generalizable person re-identification. In Proceedings of the 28th ACM international conference on multimedia, pages 3422–3430, 2020.
  47. Person transfer gan to bridge domain gap for person re-identification. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 79–88, 2018.
  48. Simple online and realtime tracking with a deep association metric. In 2017 IEEE International Conference on Image Processing (ICIP), pages 3645–3649. IEEE, 2017.
  49. Meta: Mimicking embedding via others’ aggregation for generalizable person re-identification. In Proceedings of the European conference on computer vision (ECCV), 2022.
  50. Multiple domain experts collaborative learning: Multi-source domain generalization for person re-identification. arXiv preprint arXiv:2105.12355, 2021.
  51. Barlow twins: Self-supervised learning via redundancy reduction. In International Conference on Machine Learning, pages 12310–12320. PMLR, 2021.
  52. Pha: Patch-wise high-frequency augmentation for transformer-based person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14133–14142, 2023.
  53. Unrealperson: An adaptive pipeline towards costless person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11506–11515, 2021.
  54. Relation-aware global attention for person re-identification. In Proceedings of the ieee/cvf conference on computer vision and pattern recognition, pages 3186–3195, 2020.
  55. Learning to generalize unseen domains via memory-based multi-source meta-learning for person re-identification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6277–6286, 2021.
  56. Scalable person re-identification: A benchmark. In Proceedings of the IEEE international conference on computer vision, pages 1116–1124, 2015.
  57. Person re-identification in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1367–1376, 2017.
  58. Omni-scale feature learning for person re-identification. In Proceedings of the IEEE/CVF international conference on computer vision, pages 3702–3712, 2019.
  59. Learning generalisable omni-scale representations for person re-identification. IEEE transactions on pattern analysis and machine intelligence, 44(9):5056–5069, 2021.
  60. Adaptive sparse pairwise loss for object re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 19691–19701, 2023.
  61. Identity-guided human semantic parsing for person re-identification. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16, pages 346–363. Springer, 2020.

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

Tweets

Sign up for free to view the 1 tweet with 3 likes about this paper.

Sign Up for Free