Bias-Compensated Integral Regression for Human Pose Estimation

• URL: http://arxiv.org/abs/2301.10431v1
• Date: Wed, 25 Jan 2023 06:54:04 GMT
• Title: Bias-Compensated Integral Regression for Human Pose Estimation
• Authors: Kerui Gu, Linlin Yang, Michael Bi Mi, Angela Yao
• Abstract summary: This paper uncovers an induced bias from integral regression that results from combining the softmax and the expectation operation. We propose Bias Compensated Integral Regression (BCIR), an integral regression-based framework that compensates for the bias. BCIR is faster to train and more accurate than the original integral regression, making it competitive with state-of-the-art detection methods.
• Score: 21.75308054647583
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In human and hand pose estimation, heatmaps are a crucial intermediate representation for a body or hand keypoint. Two popular methods to decode the heatmap into a final joint coordinate are via an argmax, as done in heatmap detection, or via softmax and expectation, as done in integral regression. Integral regression is learnable end-to-end, but has lower accuracy than detection. This paper uncovers an induced bias from integral regression that results from combining the softmax and the expectation operation. This bias often forces the network to learn degenerately localized heatmaps, obscuring the keypoint's true underlying distribution and leads to lower accuracies. Training-wise, by investigating the gradients of integral regression, we show that the implicit guidance of integral regression to update the heatmap makes it slower to converge than detection. To counter the above two limitations, we propose Bias Compensated Integral Regression (BCIR), an integral regression-based framework that compensates for the bias. BCIR also incorporates a Gaussian prior loss to speed up training and improve prediction accuracy. Experimental results on both the human body and hand benchmarks show that BCIR is faster to train and more accurate than the original integral regression, making it competitive with state-of-the-art detection methods.

Related papers

• Poseur: Direct Human Pose Regression with Transformers [119.79232258661995]
  We propose a direct, regression-based approach to 2D human pose estimation from single images. Our framework is end-to-end differentiable, and naturally learns to exploit the dependencies between keypoints. Ours is the first regression-based approach to perform favorably compared to the best heatmap-based pose estimation methods.
  arXiv  Detail & Related papers  (2022-01-19T04:31:57Z)
• Predicting Rebar Endpoints using Sin Exponential Regression Model [4.129225533930966]
  We propose a method to detect and track rebar endpoint images entering the machine vision camera based on YOLO (You Only Look Once)v3. The proposed method solves the problem of large prediction error rates for frame locations where rebar endpoints are far away in OPPDet models.
  arXiv  Detail & Related papers  (2021-10-18T00:38:00Z)
• Human Pose Regression with Residual Log-likelihood Estimation [48.30425850653223]
  We propose a novel regression paradigm with Residual Log-likelihood Estimation (RLE) to capture the underlying output distribution. RLE learns the change of the distribution instead of the unreferenced underlying distribution to facilitate the training process. Compared to the conventional regression paradigm, regression with RLE bring 12.4 mAP improvement on MSCOCO without any test-time overhead.
  arXiv  Detail & Related papers  (2021-07-23T15:06:31Z)
• Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation [63.623787834984206]
  We propose the scale-adaptive heatmap regression (SAHR) method, which can adaptively adjust the standard deviation for each keypoint. SAHR may aggravate the imbalance between fore-background samples, which potentially hurts the improvement of SAHR. We also introduce the weight-adaptive heatmap regression (WAHR) to help balance the fore-background samples.
  arXiv  Detail & Related papers  (2020-12-30T14:39:41Z)
• Ridge Regression with Frequent Directions: Statistical and Optimization Perspectives [1.0152838128195465]
  We show that acrshortfd can be used in the optimization setting through an iterative scheme which yields high-accuracy solutions. This improves on randomized approaches which need to compromise the need for a new sketch every iteration with speed of convergence.
  arXiv  Detail & Related papers  (2020-11-06T21:40:38Z)
• Heatmap Regression via Randomized Rounding [105.75014893647538]
  We propose a simple yet effective quantization system to address the sub-pixel localization problem. The proposed system encodes the fractional part of numerical coordinates into the ground truth heatmap using a probabilistic approach during training.
  arXiv  Detail & Related papers  (2020-09-01T04:54:22Z)
• Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint Estimates [76.51095823248104]
  We present several schemes that are rarely or unthoroughly studied before for improving keypoint detection and grouping (keypoint regression) performance. First, we exploit the keypoint heatmaps for pixel-wise keypoint regression instead of separating them for improving keypoint regression. Second, we adopt a pixel-wise spatial transformer network to learn adaptive representations for handling the scale and orientation variance. Third, we present a joint shape and heatvalue scoring scheme to promote the estimated poses that are more likely to be true poses.
  arXiv  Detail & Related papers  (2020-06-28T01:14:59Z)
• Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift [81.74795324629712]
  We call prediction-time batch normalization, which significantly improves model accuracy and calibration under covariate shift. We show that prediction-time batch normalization provides complementary benefits to existing state-of-the-art approaches for improving robustness. The method has mixed results when used alongside pre-training, and does not seem to perform as well under more natural types of dataset shift.
  arXiv  Detail & Related papers  (2020-06-19T05:08:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.