Papers
Topics
Authors
Recent
Search
2000 character limit reached

On the Calibration of Human Pose Estimation

Published 28 Nov 2023 in cs.CV | (2311.17105v1)

Abstract: Most 2D human pose estimation frameworks estimate keypoint confidence in an ad-hoc manner, using heuristics such as the maximum value of heatmaps. The confidence is part of the evaluation scheme, e.g., AP for the MSCOCO dataset, yet has been largely overlooked in the development of state-of-the-art methods. This paper takes the first steps in addressing miscalibration in pose estimation. From a calibration point of view, the confidence should be aligned with the pose accuracy. In practice, existing methods are poorly calibrated. We show, through theoretical analysis, why a miscalibration gap exists and how to narrow the gap. Simply predicting the instance size and adjusting the confidence function gives considerable AP improvements. Given the black-box nature of deep neural networks, however, it is not possible to fully close this gap with only closed-form adjustments. As such, we go one step further and learn network-specific adjustments by enforcing consistency between confidence and pose accuracy. Our proposed Calibrated ConfidenceNet (CCNet) is a light-weight post-hoc addition that improves AP by up to 1.4% on off-the-shelf pose estimation frameworks. Applied to the downstream task of mesh recovery, CCNet facilitates an additional 1.0mm decrease in 3D keypoint error.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. Deep evidential regression. In NeurIPS, 2020.
  2. 2D human pose estimation: New benchmark and state of the art analysis. In CVPR, 2014.
  3. Plausible uncertainties for human pose regression. In ICCV, 2023.
  4. MHEntropy: Entropy meets multiple hypotheses for pose and shape recovery. In ICCV, 2023.
  5. Addressing failure prediction by learning model confidence. In NeurIPS, 2019.
  6. MUAD: Multiple uncertainties for autonomous driving, a benchmark for multiple uncertainty types and tasks. In BMVC, 2022.
  7. Dive deeper into integral pose regression. In ICLR, 2021a.
  8. Removing the bias of integral pose regression. In ICCV, 2021b.
  9. On calibration of modern neural networks. In ICML, 2017.
  10. Uncertainty estimates and multi-hypotheses networks for optical flow. In ECCV, 2018.
  11. Whole-body human pose estimation in the wild. In ECCV, 2020.
  12. What uncertainties do we need in bayesian deep learning for computer vision? In NIPS, 2017.
  13. Adam: A method for stochastic optimization. In ICLR, 2014.
  14. Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In ICCV, 2019.
  15. Calibrated and sharp uncertainties in deep learning via density estimation. In ICML, 2022.
  16. Simple and scalable predictive uncertainty estimation using deep ensembles. In NIPS, 2017.
  17. Human pose regression with residual log-likelihood estimation. In ICCV, 2021a.
  18. Pose recognition with cascade transformers. In CVPR, 2021b.
  19. Microsoft COCO: Common objects in context. In ECCV, 2014.
  20. SMPL: A skinned multi-person linear model. In SIGGRAPH Asia, 2015.
  21. Poseur: Direct human pose regression with transformers. In ECCV, 2022.
  22. Towards accurate multi-person pose estimation in the wild. In CVPR, 2017.
  23. Multiclass confidence and localization calibration for object detection. In CVPR, 2023.
  24. Multi-hypothesis 3D human pose estimation metrics favor miscalibrated distributions. In arXiv, 2022.
  25. Stochastic optimization of areas under precision-recall curves with provable convergence. In NeurIPS, 2021.
  26. Benchmarking and error diagnosis in multi-instance pose estimation. In ICCV, 2017.
  27. End-to-end multi-person pose estimation with transformers. In CVPR, 2022.
  28. Distribution calibration for regression. In ICML, 2019.
  29. Deep high-resolution representation learning for human pose estimation. In CVPR, 2019.
  30. Integral human pose regression. In ECCV, 2018.
  31. DeepPose: Human pose estimation via deep neural networks. In CVPR, 2014.
  32. Probabilistic monocular 3D human pose estimation with normalizing flows. In ICCV, 2021.
  33. Point-set anchors for object detection, instance segmentation and pose estimation. In ECCV, 2020.
  34. Simple baselines for human pose estimation and tracking. In ECCV, 2018.
  35. ViTPose: Simple vision transformer baselines for human pose estimation. In NeurIPS, 2022.
  36. SLURP: Side learning uncertainty for regression problems. In BMVC, 2021.
  37. Discretization-induced Dirichlet posterior for robust uncertainty quantification on regression. In arXiv, 2023.
  38. Distribution-aware coordinate representation for human pose estimation. In CVPR, 2020.
  39. Adding conditional control to text-to-image diffusion models. In ICCV, 2023.
Citations (4)
View on Semantic Scholar

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

Authors (3)

  1. Kerui Gu 
  2. Rongyu Chen 
  3. Angela Yao 

Collections

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

Sign Up