mlsanityData to 7 Oct 2026

Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module

arXiv 2303.04346 ↗First posted 8 Mar 2023cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

In this paper, we delve into semi-supervised 2D human pose estimation. The previous method ignored two problems: (i) When conducting interactive training between large model and lightweight model, the pseudo label of lightweight model will be used to guide large models. (ii) The negative impact of noise pseudo labels on training. Moreover, the labels used for 2D human pose estimation are relatively complex: keypoint category and keypoint position. To solve the problems mentioned above, we propose a semi-supervised 2D human pose estimation framework driven by a position inconsistency pseudo label correction module (SSPCM). We introduce an additional auxiliary teacher and use the pseudo labels generated by the two teacher model in different periods to calculate the inconsistency score and remove outliers. Then, the two teacher models are updated through interactive training, and the student model is updated using the pseudo labels generated by two teachers. To further improve the performance of the student model, we use the semi-supervised Cut-Occlude based on pseudo keypoint perception to generate more hard and effective samples. In addition, we also proposed a new indoor overhead fisheye human keypoint dataset WEPDTOF-Pose. Extensive experiments demonstrate that our method outperforms the previous best semi-supervised 2D human pose estimation method. We will release the code and dataset at https://github.com/hlz0606/SSPCM.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 49 of its 57 references that are in the map. First posted on arXiv 8 Mar 2023.

Builds on

49 of 57 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  8. 2014Going Deeper with Convolutionscited by 4,231
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  10. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  11. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  12. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
37 more
  1. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  2. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  3. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  4. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  5. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  6. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  7. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 507
  8. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  9. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  10. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  11. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  12. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  13. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  14. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  15. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  16. 2021Revisiting Skeleton-based Action Recognitioncited by 256
  17. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  18. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  19. 2018Acquisition of Localization Confidence for Accurate Object Detectioncited by 174
  20. 2019Distribution-Aware Coordinate Representation for Human Pose Estimationcited by 165
  21. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  22. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  23. 2017Data Distillation: Towards Omni-Supervised Learningcited by 126
  24. 2019The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimationcited by 79
  25. 2018Fast Human Pose Estimationcited by 68
  26. 2019Rethinking on Multi-Stage Networks for Human Pose Estimationcited by 58
  27. 2021Online Knowledge Distillation for Efficient Pose Estimationcited by 55
  28. 2022PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detectioncited by 51
  29. 2021Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detectioncited by 48
  30. 2018Multi-Scale Structure-Aware Network for Human Pose Estimationcited by 37
  31. 2020JOLO-GCN: Mining Joint-Centered Light-Weight Information for Skeleton-Based Action Recognitioncited by 33
  32. 2022Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detectioncited by 23
  33. 2020Adversarial Semantic Data Augmentation for Human Pose Estimationcited by 22
  34. 2019Human Pose Estimation with Spatial Contextual Informationcited by 21
  35. 2020An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimationcited by 21
  36. 2020RAPiD: Rotation-Aware People Detection in Overhead Fisheye Imagescited by 17
  37. 2022DH-AUG: DH Forward Kinematics Model Driven Augmentation for 3D Human Pose Estimationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 4; 2025: 2; 2026: 2.

10 papers.

  1. 2024Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimationcited by 19
  2. 2024Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditionscited by 7
  3. 2025From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Camerascited by 3
  4. 2023Improving 2D Human Pose Estimation in Rare Camera Views with Synthetic Datacited by 2
  5. 2024Semi-Supervised Unconstrained Head Pose Estimation in the Wildcited by 2
  6. 2025An uncertainty-aware framework for data-efficient multi-view animal pose estimationcited by 2
  7. 2026Expanding mmWave Datasets for Human Pose Estimation with Unlabeled Data and LiDAR Datasetscited by 1
  8. 2026MoViD: View-Invariant 3D Human Pose Estimation via Motion-View Disentanglementcited by 1
  9. 2023Denoising and Selecting Pseudo-Heatmaps for Semi-Supervised Human Pose Estimationcited by 0
  10. 2024Boosting Semi-Supervised 2D Human Pose Estimation by Revisiting Data Augmentation and Consistency Trainingcited by 0