Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices
Xuan Shen, Geng Yuan, Wei Niu, Xiaolong Ma, Jiexiong Guan, Zhengang Li, Bin Ren, Yanzhi Wang
Abstract
The rapid development of autonomous driving, abnormal behavior detection, and behavior recognition makes an increasing demand for multi-person pose estimation-based applications, especially on mobile platforms. However, to achieve high accuracy, state-of-the-art methods tend to have a large model size and complex post-processing algorithm, which costs intense computation and long end-to-end latency. To solve this problem, we propose an architecture optimization and weight pruning framework to accelerate inference of multi-person pose estimation on mobile devices. With our optimization framework, we achieve up to 2.51X faster model inference speed with higher accuracy compared to representative lightweight multi-person pose estimator.
BibTeX
@inproceedings{ijcai2021p715,
title = {Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices},
author = {Shen, Xuan and Yuan, Geng and Niu, Wei and Ma, Xiaolong and Guan, Jiexiong and Li, Zhengang and Ren, Bin and Wang, Yanzhi},
booktitle = {Proceedings of the Thirtieth International Joint Conference on
Artificial Intelligence, {IJCAI-21}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Zhi-Hua Zhou},
pages = {5012--5015},
year = {2021},
month = {8},
note = {Demo Track},
doi = {10.24963/ijcai.2021/715},
url = {https://doi.org/10.24963/ijcai.2021/715},
}