Paper
8 June 2023 Process knowledge distillation for multi-person pose estimation
Zhifeng Zhao, Zheng Yan, MingLei She, Guodong Chen
Author Affiliations +
Proceedings Volume 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023); 127072P (2023) https://doi.org/10.1117/12.2680994
Event: International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 2023, Changsha, China
Abstract
Existing multi-person pose estimation methods show a tendency for the parameters in the model to become increasingly large in order to improve generalisation performance, requiring huge computational resources. Therefore, we propose a lightweight multi-person pose estimation method called PKDHP (Process Knowledge Distillation for Human Pose estimation), which applies knowledge distillation to pose estimation. PKDHP treats the training process of student models in knowledge distillation as a human learning process, specifically, PKDHP proposes the CABF module to replace the ABF module in ReviewKD aiming to guide the lower level feature through the model's higher level feature, and proposes the Transfer knowledge distillation method to force the student model to imitate the process of feature transfer from the teacher model, thus further simulating the human learning style. Compared with other knowledge distillation methods, we use the same model parameters on two multi-person pose estimation datasets (COCO and MPII) to achieve higher performance.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhifeng Zhao, Zheng Yan, MingLei She, and Guodong Chen "Process knowledge distillation for multi-person pose estimation", Proc. SPIE 12707, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023), 127072P (8 June 2023); https://doi.org/10.1117/12.2680994
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Pose estimation

Performance modeling

Education and training

Autoregressive models

Feature fusion

Ablation

Data modeling

Back to Top