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

07/12/2020 ∙ by Feiyu Yang, et al. ∙ 5

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. Specifically, equipped with DAEC, the SimpleBaseline-ResNet152-256x192 and HRNet-W48-256x192 are significantly improved by 2.6 72.6 ResNet-152-256x256 frameworks enjoy even more dramatic promotions of 8.4 7.8 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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 6

Code Repositories

DAEC

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


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.