Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
158 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

Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimation (2310.00099v1)

Published 29 Sep 2023 in cs.CV

Abstract: We propose a new semi-supervised learning design for human pose estimation that revisits the popular dual-student framework and enhances it two ways. First, we introduce a denoising scheme to generate reliable pseudo-heatmaps as targets for learning from unlabeled data. This uses multi-view augmentations and a threshold-and-refine procedure to produce a pool of pseudo-heatmaps. Second, we select the learning targets from these pseudo-heatmaps guided by the estimated cross-student uncertainty. We evaluate our proposed method on multiple evaluation setups on the COCO benchmark. Our results show that our model outperforms previous state-of-the-art semi-supervised pose estimators, especially in extreme low-data regime. For example with only 0.5K labeled images our method is capable of surpassing the best competitor by 7.22 mAP (+25% absolute improvement). We also demonstrate that our model can learn effectively from unlabeled data in the wild to further boost its generalization and performance.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (58)
  1. Pseudo-labeling and confirmation bias in deep semi-supervised learning. In IJCNN, 2020.
  2. Learning with pseudo-ensembles. arXiv preprint arXiv:1412.4864, 2014.
  3. Remixmatch: Semi-supervised learning with distribution matching and augmentation anchoring. In ICLR, 2020.
  4. Mixmatch: A holistic approach to semi-supervised learning. arXiv preprint arXiv:1905.02249, 2019.
  5. Combining labeled and unlabeled data with co-training. In CLT, 1998.
  6. Weight uncertainty in neural network. In ICML, 2015.
  7. Leo Breiman. Random forests. Machine learning, 2001.
  8. Semi-supervised learning (chapelle, o. et al., eds.; 2006)[book reviews]. IEEE TNN, 2009.
  9. Semi-supervised and unsupervised deep visual learning: A survey. IEEE TPAMI, 2022.
  10. Cascaded pyramid network for multi-person pose estimation. In CVPR, 2018.
  11. Imagenet: A large-scale hierarchical image database. In CVPR, 2009.
  12. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In ICML, 2016.
  13. Deep residual learning for image recognition. In CVPR, 2016.
  14. Improving landmark localization with semi-supervised learning. In CVPR, 2018.
  15. Label propagation for deep semi-supervised learning. In CVPR, 2019.
  16. Consistency-based semi-supervised learning for object detection. In NeurIPS, 2019.
  17. Semi-supervised hierarchical models for 3d human pose reconstruction. In CVPR, 2007.
  18. Dual student: Breaking the limits of the teacher in semi-supervised learning. In ICCV, 2019.
  19. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  20. Temporal ensembling for semi-supervised learning. arXiv preprint arXiv:1610.02242, 2016.
  21. Simple and scalable predictive uncertainty estimation using deep ensembles. NeurIPS, 30, 2017.
  22. Dong-Hyun Lee et al. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In ICMLW, 2013.
  23. Microsoft coco: Common objects in context. In ECCV, 2014.
  24. Unbiased teacher for semi-supervised object detection. arXiv preprint arXiv:2102.09480, 2021.
  25. Unbiased teacher v2: Semi-supervised object detection for anchor-free and anchor-based detectors. In CVPR, 2022.
  26. Predictive uncertainty estimation via prior networks. NeurIPS, 2018.
  27. Tom M Mitchell. Generalization as search. Artificial intelligence, 1982.
  28. Multiview-consistent semi-supervised learning for 3d human pose estimation. In CVPR, 2020.
  29. Semi-supervised keypoint localization. arXiv preprint arXiv:2101.07988, 2021.
  30. Uncertainty-aware self-training for few-shot text classification. In H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems, volume 33, pages 21199–21212. Curran Associates, Inc., 2020.
  31. Stacked hourglass networks for human pose estimation. In ECCV, 2016.
  32. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In CVPR, 2015.
  33. Towards accurate multi-person pose estimation in the wild. In CVPR, 2017.
  34. 3d human pose estimation in video with temporal convolutions and semi-supervised training. In CVPR, 2019.
  35. Data distillation: Towards omni-supervised learning. In CVPR, 2018.
  36. In defense of pseudo-labeling: An uncertainty-aware pseudo-label selection framework for semi-supervised learning. arXiv preprint arXiv:2101.06329, 2021.
  37. Regularization with stochastic transformations and perturbations for deep semi-supervised learning. arXiv preprint arXiv:1606.04586, 2016.
  38. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. In NeurIPS, 2020.
  39. A simple semi-supervised learning framework for object detection. arXiv preprint arXiv:2005.04757, 2020.
  40. Deep high-resolution representation learning for human pose estimation. In CVPR, 2019.
  41. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In NeurIPS, 2017.
  42. Joint training of a convolutional network and a graphical model for human pose estimation. In NeurIPS, 2014.
  43. Semi-and weakly-supervised human pose estimation. CVIU, 2018.
  44. Uncertainty estimation using a single deep deterministic neural network. In ICML. PMLR, 2020.
  45. Pseudo-labeled auto-curriculum learning for semi-supervised keypoint localization. arXiv preprint arXiv:2201.08613, 2022.
  46. Large-scale datasets for going deeper in image understanding. In ICME, 2019.
  47. 3d semi-supervised learning with uncertainty-aware multi-view co-training. In WACV, 2020.
  48. Simple baselines for human pose estimation and tracking. In ECCV, 2018.
  49. Unsupervised data augmentation for consistency training. In NeurIPS, 2020.
  50. Self-training with noisy student improves imagenet classification. In CVPR, 2020.
  51. An empirical study of the collapsing problem in semi-supervised 2d human pose estimation. In ICCV, 2021.
  52. End-to-end semi-supervised object detection with soft teacher. In ICCV, 2021.
  53. Articulated human detection with flexible mixtures of parts. IEEE TPAMI, 2013.
  54. Uncertainty-aware self-ensembling model for semi-supervised 3d left atrium segmentation. In MICCAI, 2019.
  55. Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. In NeurIPS, 2021.
  56. Instant-teaching: An end-to-end semi-supervised object detection framework. In CVPR, 2021.
  57. Introduction to semi-supervised learning. Synthesis lectures on artificial intelligence and machine learning, 2009.
  58. Xiaojin Jerry Zhu. Semi-supervised learning literature survey. Technical report, University of Wisconsin-Madison Department of Computer Sciences, 2005.
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