Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation [article]

Qun Li, Ziyi Zhang, Fu Xiao, Feng Zhang, Bir Bhanu
2022 arXiv   pre-print
A high-resolution network exhibits remarkable capability in extracting multi-scale features for human pose estimation, but fails to capture long-range interactions between joints and has high computational complexity. To address these problems, we present a Dynamic lightweight High-Resolution Network (Dite-HRNet), which can efficiently extract multi-scale contextual information and model long-range spatial dependency for human pose estimation. Specifically, we propose two methods, dynamic split
more » ... convolution and adaptive context modeling, and embed them into two novel lightweight blocks, which are named dynamic multi-scale context block and dynamic global context block. These two blocks, as the basic component units of our Dite-HRNet, are specially designed for the high-resolution networks to make full use of the parallel multi-resolution architecture. Experimental results show that the proposed network achieves superior performance on both COCO and MPII human pose estimation datasets, surpassing the state-of-the-art lightweight networks. Code is available at: https://github.com/ZiyiZhang27/Dite-HRNet.
arXiv:2204.10762v3 fatcat:2lz7oxjp6zcmzbg4gzd3cejzq4