SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation

Authors

  • Jiabin Zhang Institute of Automation, Chinese Academy of Sciences
  • Zheng Zhu Tsinghua University
  • Jiwen Lu Tsinghua University
  • Junjie Huang XForwardAI Technology Co.,Ltd
  • Guan Huang XForwardAI Technology Co.,Ltd
  • Jie Zhou Tsinghua University

Keywords:

Biometrics, Face, Gesture & Pose

Abstract

The practical application requests both accuracy and efficiency on multi-person pose estimation algorithms. But the high accuracy and fast inference speed are dominated by top-down methods and bottom-up methods respectively. To make a better trade-off between accuracy and efficiency, we propose a novel multi-person pose estimation framework, SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation (SIMPLE). Specifically, in the training process, we enable SIMPLE to mimic the pose knowledge from the high-performance top-down pipeline, which significantly promotes SIMPLE's accuracy while maintaining its high efficiency during inference. Besides, SIMPLE formulates human detection and pose estimation as a unified point learning framework to complement each other in single-network. This is quite different from previous works where the two tasks may interfere with each other. To the best of our knowledge, both mimicking strategy between different method types and unified point learning are firstly proposed in pose estimation. In experiments, our approach achieves the new state-of-the-art performance among bottom-up methods on the COCO, MPII and PoseTrack datasets. Compared with the top-down approaches, SIMPLE has comparable accuracy and faster inference speed.

Downloads

Published

2021-05-18

How to Cite

Zhang, J., Zhu, Z., Lu, J., Huang, J., Huang, G., & Zhou, J. (2021). SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(4), 3342-3350. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16446

Issue

Section

AAAI Technical Track on Computer Vision III