Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915820624412672 |
|---|---|
| author | Li, Qun Zhang, Ziyi Xiao, Fu Zhang, Feng Bhanu, Bir |
| author_facet | Li, Qun Zhang, Ziyi Xiao, Fu Zhang, Feng Bhanu, Bir |
| contents | 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 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2204_10762 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation Li, Qun Zhang, Ziyi Xiao, Fu Zhang, Feng Bhanu, Bir Computer Vision and Pattern Recognition 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 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. |
| title | Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2204.10762 |