AgentPose: Progressive Distribution Alignment via Feature Agent for Human Pose Distillation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Feng, Liu, Jinwei, Zhu, Xiatian, Chen, Lei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916566266806272
author Zhang, Feng
Liu, Jinwei
Zhu, Xiatian
Chen, Lei
author_facet Zhang, Feng
Liu, Jinwei
Zhu, Xiatian
Chen, Lei
contents Pose distillation is widely adopted to reduce model size in human pose estimation. However, existing methods primarily emphasize the transfer of teacher knowledge while often neglecting the performance degradation resulted from the curse of capacity gap between teacher and student. To address this issue, we propose AgentPose, a novel pose distillation method that integrates a feature agent to model the distribution of teacher features and progressively aligns the distribution of student features with that of the teacher feature, effectively overcoming the capacity gap and enhancing the ability of knowledge transfer. Our comprehensive experiments conducted on the COCO dataset substantiate the effectiveness of our method in knowledge transfer, particularly in scenarios with a high capacity gap.
format Preprint
id arxiv_https___arxiv_org_abs_2501_08088
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AgentPose: Progressive Distribution Alignment via Feature Agent for Human Pose Distillation
Zhang, Feng
Liu, Jinwei
Zhu, Xiatian
Chen, Lei
Computer Vision and Pattern Recognition
Pose distillation is widely adopted to reduce model size in human pose estimation. However, existing methods primarily emphasize the transfer of teacher knowledge while often neglecting the performance degradation resulted from the curse of capacity gap between teacher and student. To address this issue, we propose AgentPose, a novel pose distillation method that integrates a feature agent to model the distribution of teacher features and progressively aligns the distribution of student features with that of the teacher feature, effectively overcoming the capacity gap and enhancing the ability of knowledge transfer. Our comprehensive experiments conducted on the COCO dataset substantiate the effectiveness of our method in knowledge transfer, particularly in scenarios with a high capacity gap.
title AgentPose: Progressive Distribution Alignment via Feature Agent for Human Pose Distillation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.08088