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.
@article{arxiv.2106.15304,
title = {Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices},
author = {Xuan Shen and Geng Yuan and Wei Niu and Xiaolong Ma and Jiexiong Guan and Zhengang Li and Bin Ren and Yanzhi Wang},
journal= {arXiv preprint arXiv:2106.15304},
year = {2021}
}