Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Watch Where You Head: A View-biased Domain Gap in Gait Recognition and Unsupervised Adaptation (2307.06751v3)

Published 13 Jul 2023 in cs.CV

Abstract: Gait Recognition is a computer vision task aiming to identify people by their walking patterns. Although existing methods often show high performance on specific datasets, they lack the ability to generalize to unseen scenarios. Unsupervised Domain Adaptation (UDA) tries to adapt a model, pre-trained in a supervised manner on a source domain, to an unlabelled target domain. There are only a few works on UDA for gait recognition proposing solutions to limited scenarios. In this paper, we reveal a fundamental phenomenon in adaptation of gait recognition models, caused by the bias in the target domain to viewing angle or walking direction. We then suggest a remedy to reduce this bias with a novel triplet selection strategy combined with curriculum learning. To this end, we present Gait Orientation-based method for Unsupervised Domain Adaptation (GOUDA). We provide extensive experiments on four widely-used gait datasets, CASIA-B, OU-MVLP, GREW, and Gait3D, and on three backbones, GaitSet, GaitPart, and GaitGL, justifying the view bias and showing the superiority of our proposed method over prior UDA works.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. Performance evaluation of model-based gait on multi-view very large population database with pose sequences. IEEE transactions on biometrics, behavior, and identity science, 2(4):421–430, 2020.
  2. Curriculum learning. In Proceedings of the 26th annual international conference on machine learning, pages 41–48, 2009.
  3. Unsupervised and self-adaptative techniques for cross-domain person re-identification. IEEE Transactions on Information Forensics and Security, 16:4419–4434, 2021.
  4. Gaitset: Regarding gait as a set for cross-view gait recognition. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 8126–8133, 2019.
  5. Pipa: Pixel-and patch-wise self-supervised learning for domain adaptative semantic segmentation. arXiv preprint arXiv:2211.07609, 2022.
  6. A tutorial on the cross-entropy method. Annals of operations research, 134:19–67, 2005.
  7. Learning gait representation from massive unlabelled walking videos: A benchmark. arXiv preprint arXiv:2206.13964, 2022.
  8. Opengait: Revisiting gait recognition towards better practicality. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9707–9716, 2023.
  9. Gaitpart: Temporal part-based model for gait recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14225–14233, 2020.
  10. Self-ensembling for visual domain adaptation. arXiv preprint arXiv:1706.05208, 2017.
  11. Domain-adversarial training of neural networks. The journal of machine learning research, 17(1):2096–2030, 2016.
  12. Individual recognition using gait energy image. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(2):316–322, 2006.
  13. Secret: Self-consistent pseudo label refinement for unsupervised domain adaptive person re-identification. In Proceedings of the AAAI conference on artificial intelligence, volume 36, pages 879–887, 2022.
  14. In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737, 2017.
  15. Gait lateral network: Learning discriminative and compact representations for gait recognition. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part IX, pages 382–398. Springer, 2020.
  16. Hrda: Context-aware high-resolution domain-adaptive semantic segmentation. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXX, pages 372–391. Springer, 2022.
  17. Context-sensitive temporal feature learning for gait recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 12909–12918, 2021.
  18. 3d local convolutional neural networks for gait recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 14920–14929, October 2021.
  19. Adam: A method for stochastic optimization. In Proc. Int. Conf. Learn. Represent., page 1–41, 2015.
  20. Cross-species data classification by domain adaptation via discriminative heterogeneous maximum mean discrepancy. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 18(1):312–324, 2019.
  21. Adadc: Adaptive deep clustering for unsupervised domain adaptation in person re-identification. IEEE Transactions on Circuits and Systems for Video Technology, 32(6):3825–3838, 2022.
  22. Mhformer: Multi-hypothesis transformer for 3d human pose estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13147–13156, 2022.
  23. Gait recognition via semi-supervised disentangled representation learning to identity and covariate features. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13309–13319, 2020.
  24. End-to-end model-based gait recognition. In Proceedings of the Asian conference on computer vision, 2020.
  25. Adaptive batch normalization for practical domain adaptation. Pattern Recognition, 80:109–117, 2018.
  26. Gaitedge: Beyond plain end-to-end gait recognition for better practicality. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part V, pages 375–390. Springer, 2022.
  27. A model-based gait recognition method with body pose and human prior knowledge. Pattern Recognition, 98:107069, 2020.
  28. Gait recognition with multiple-temporal-scale 3d convolutional neural network. In Proceedings of the 28th ACM international conference on multimedia, pages 3054–3062, 2020.
  29. Gait recognition via effective global-local feature representation and local temporal aggregation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 14648–14656, 2021.
  30. Deep unsupervised domain adaptation: A review of recent advances and perspectives. APSIPA Transactions on Signal and Information Processing, 11(1), 2022.
  31. Forensic gait analysis and recognition: standards of evidence admissibility. Journal of forensic sciences, 64(5):1294–1303, 2019.
  32. Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426, 2018.
  33. Applications of a simple characterization of human gait in surveillance. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 40(4):1009–1020, 2010.
  34. Gait-based identification for elderly users in wearable healthcare systems. Information fusion, 53:134–144, 2020.
  35. Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition. IPSJ transactions on Computer Vision and Applications, 10:1–14, 2018.
  36. Gaitgraph: Graph convolutional network for skeleton-based gait recognition. In 2021 IEEE International Conference on Image Processing (ICIP), pages 2314–2318. IEEE, 2021.
  37. Adversarial discriminative domain adaptation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017.
  38. Human identification using temporal information preserving gait template. IEEE transactions on pattern analysis and machine intelligence, 34(11):2164–2176, 2011.
  39. From indoor to outdoor: Unsupervised domain adaptive gait recognition. arXiv preprint arXiv:2211.11155, 2022.
  40. Uncertainty-aware clustering for unsupervised domain adaptive object re-identification. IEEE Transactions on Multimedia, pages 1–1, 2022.
  41. A survey of unsupervised deep domain adaptation. ACM Transactions on Intelligent Systems and Technology (TIST), 11(5):1–46, 2020.
  42. Cdtrans: Cross-domain transformer for unsupervised domain adaptation. arXiv preprint arXiv:2109.06165, 2021.
  43. Spatial-temporal graph convolutional network for skeleton-based gait recognition. In 2022 3rd International Conference on Pattern Recognition and Machine Learning (PRML), pages 77–82, 2022.
  44. A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. In 18th International Conference on Pattern Recognition (ICPR’06), volume 4, pages 441–444, 2006.
  45. Zhaoxiang Zhang. A gait recognition method for a moving target image in sports based on a decision tree. International Journal of Biometrics, 13(2-3):165–179, 2021.
  46. Gait recognition in the wild with dense 3d representations and a benchmark. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 20228–20237, June 2022.
  47. Trand: Transferable neighborhood discovery for unsupervised cross-domain gait recognition. In 2021 IEEE International Symposium on Circuits and Systems (ISCAS), pages 1–5. IEEE, 2021.
  48. Exploiting sample uncertainty for domain adaptive person re-identification. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 3538–3546, 2021.
  49. Gait recognition using 3-d human body shape inference. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 909–918, 2023.
  50. Patch-mix transformer for unsupervised domain adaptation: A game perspective. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3561–3571, 2023.
  51. Gait recognition in the wild: A benchmark. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 14789–14799, October 2021.
Citations (1)
View on Semantic Scholar

Summary

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

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