Train Your Data Processor: Distribution-Aware and Error-Compensation Coordinate Decoding for Human Pose Estimation

• URL: http://arxiv.org/abs/2007.05887v4
• Date: Fri, 17 Jul 2020 04:03:25 GMT
• Title: Train Your Data Processor: Distribution-Aware and Error-Compensation Coordinate Decoding for Human Pose Estimation
• Authors: Feiyu Yang, Zhan Song, Zhenzhong Xiao, Yu Chen, Zhe Pan, Min Zhang, Min Xue, Yaoyang Mo, Yao Zhang, Guoxiong Guan, Beibei Qian
• Abstract summary: We study the heatmap decoding processing with a particular focus on the errors introduced throughout the prediction process. Thereout propose a Distribution-Aware and Error-Compensation Coordinate Decoding (DAEC) DAEC learns its decoding strategy from training data and remarkably improves the performance of state-of-the-art human pose estimation models.
• Score: 14.816632698778049
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, the leading performance of human pose estimation is dominated by heatmap based methods. While being a fundamental component of heatmap processing, heatmap decoding (i.e. transforming heatmaps to coordinates) receives only limited investigations, to our best knowledge. This work fills the gap by studying the heatmap decoding processing with a particular focus on the errors introduced throughout the prediction process. We found that the errors of heatmap based methods are surprisingly significant, which nevertheless was universally ignored before. In view of the discovered importance, we further reveal the intrinsic limitations of the previous widely used heatmap decoding methods and thereout propose a Distribution-Aware and Error-Compensation Coordinate Decoding (DAEC). Serving as a model-agnostic plug-in, DAEC learns its decoding strategy from training data and remarkably improves the performance of a variety of state-of-the-art human pose estimation models with negligible extra computation. Specifically, equipped with DAEC, the SimpleBaseline-ResNet152-256x192 and HRNet-W48-256x192 are significantly improved by 2.6 AP and 2.9 AP achieving 72.6 AP and 75.7 AP on COCO, respectively. Moreover, the HRNet-W32-256x256 and ResNet-152-256x256 frameworks enjoy even more dramatic promotions of 8.4% and 7.8% on MPII with PCKh0.1 metric. Extensive experiments performed on these two common benchmarks, demonstrates that DAEC exceeds its competitors by considerable margins, backing up the rationality and generality of our novel heatmap decoding idea. The project is available at https://github.com/fyang235/DAEC.

Related papers

• Lightweight Super-Resolution Head for Human Pose Estimation [42.51588635059534]
  Heatmap-based methods have become the mainstream method for pose estimation. However, heatmap-based approaches suffer from significant quantization errors with downscale heatmaps. We propose SRPose to reduce the quantization error and dependence on further post-processing.
  arXiv  Detail & Related papers  (2023-07-31T15:35:34Z)
• DistilPose: Tokenized Pose Regression with Heatmap Distillation [81.21273854769765]
  We propose a novel human pose estimation framework termed DistilPose, which bridges the gaps between heatmap-based and regression-based methods. DistilPose maximizes the transfer of knowledge from the teacher model (heatmap-based) to the student model (regression-based) through Token-distilling (TDE) and Simulated Heatmaps.
  arXiv  Detail & Related papers  (2023-03-04T16:56:29Z)
• Precise Single-stage Detector [2.2719729705587155]
  We propose a modified version of Single Shot Multibox Detector (SSD) named Precise Single Stage Detector (PSSD) In order to address these aforementioned issues, we propose a new architecture, named Precise Single Stage Detector (PSSD)
  arXiv  Detail & Related papers  (2022-10-09T12:58:37Z)
• Heatmap Distribution Matching for Human Pose Estimation [12.524484316923333]
  We show that optimizing the heatmap prediction in such a way, the model performance of body joint localization may not be consistently improved. We propose to formulate the optimization of the heatmap prediction as a distribution matching problem between the predicted heatmap and the dot annotation of the body joint. We show the effectiveness of our proposed method through extensive experiments on the COCO dataset and the MPII dataset.
  arXiv  Detail & Related papers  (2022-10-03T07:21:30Z)
• Lightweight Human Pose Estimation Using Heatmap-Weighting Loss [7.830376406370752]
  We introduce an attention mechanism that utilizes original, inter-level, and intra-level information to intensify the accuracy. We also propose a novel loss function called heatmap weighting loss, which generates weights for each pixel on the heatmap that makes the model more focused on keypoints.
  arXiv  Detail & Related papers  (2022-05-21T14:26:14Z)
• 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)
• Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation [79.78017059539526]
  We propose a new heatmap-free keypoint estimation method in which individual keypoints and sets of spatially related keypoints (i.e., poses) are modeled as objects within a dense single-stage anchor-based detection framework. In experiments, we observe that KAPAO is significantly faster and more accurate than previous methods, which suffer greatly from heatmap post-processing. Our large model, KAPAO-L, achieves an AP of 70.6 on the Microsoft COCO Keypoints validation set without test-time augmentation.
  arXiv  Detail & Related papers  (2021-11-16T15:36:44Z)
• FasterPose: A Faster Simple Baseline for Human Pose Estimation [65.8413964785972]
  We propose a design paradigm for cost-effective network with LR representation for efficient pose estimation, named FasterPose. We study the training behavior of FasterPose, and formulate a novel regressive cross-entropy (RCE) loss function for accelerating the convergence. Compared with the previously dominant network of pose estimation, our method reduces 58% of the FLOPs and simultaneously gains 1.3% improvement of accuracy.
  arXiv  Detail & Related papers  (2021-07-07T13:39:08Z)
• 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)
• 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)
• Joint COCO and Mapillary Workshop at ICCV 2019 Keypoint Detection Challenge Track Technical Report: Distribution-Aware Coordinate Representation for Human Pose Estimation [36.73217430761146]
  We focus on the coordinate representation in human pose estimation. We propose a principled distribution-aware decoding method. Taking them together, we formulate a novel Distribution-Aware coordinate Representation for Keypoint (DARK) method.
  arXiv  Detail & Related papers  (2020-03-13T10:22:36Z)

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.