Fast Human Pose Estimation

CVPR 2019  ·  Feng Zhang, Xiatian Zhu, Mao Ye ·

Existing human pose estimation approaches often only consider how to improve the model generalisation performance, but putting aside the significant efficiency problem. This leads to the development of heavy models with poor scalability and cost-effectiveness in practical use. In this work, we investigate the under-studied but practically critical pose model efficiency problem. To this end, we present a new Fast Pose Distillation (FPD) model learning strategy. Specifically, the FPD trains a lightweight pose neural network architecture capable of executing rapidly with low computational cost. It is achieved by effectively transferring the pose structure knowledge of a strong teacher network. Extensive evaluations demonstrate the advantages of our FPD method over a broad range of state-of-the-art pose estimation approaches in terms of model cost-effectiveness on two standard benchmark datasets, MPII Human Pose and Leeds Sports Pose.

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Pose Estimation Leeds Sports Poses FPD PCK 90.8% # 9
Pose Estimation MPII Human Pose FPD PCKh-0.5 91.1 # 22

Methods


No methods listed for this paper. Add relevant methods here