Online Knowledge Distillation for Efficient Pose Estimation

08/04/2021
by   Zheng Li, et al.
0

Existing state-of-the-art human pose estimation methods require heavy computational resources for accurate predictions. One promising technique to obtain an accurate yet lightweight pose estimator is knowledge distillation, which distills the pose knowledge from a powerful teacher model to a less-parameterized student model. However, existing pose distillation works rely on a heavy pre-trained estimator to perform knowledge transfer and require a complex two-stage learning procedure. In this work, we investigate a novel Online Knowledge Distillation framework by distilling Human Pose structure knowledge in a one-stage manner to guarantee the distillation efficiency, termed OKDHP. Specifically, OKDHP trains a single multi-branch network and acquires the predicted heatmaps from each, which are then assembled by a Feature Aggregation Unit (FAU) as the target heatmaps to teach each branch in reverse. Instead of simply averaging the heatmaps, FAU which consists of multiple parallel transformations with different receptive fields, leverages the multi-scale information, thus obtains target heatmaps with higher-quality. Specifically, the pixel-wise Kullback-Leibler (KL) divergence is utilized to minimize the discrepancy between the target heatmaps and the predicted ones, which enables the student network to learn the implicit keypoint relationship. Besides, an unbalanced OKDHP scheme is introduced to customize the student networks with different compression rates. The effectiveness of our approach is demonstrated by extensive experiments on two common benchmark datasets, MPII and COCO.

READ FULL TEXT

page 5

page 7

page 11

research
04/21/2021

Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimation

Although deep convolution neural networks (DCNN) have achieved excellent...
research
05/24/2023

On Correlated Knowledge Distillation for Monitoring Human Pose with Radios

In this work, we propose and develop a simple experimental testbed to st...
research
05/13/2021

When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks

Human pose estimation is a fundamental yet challenging task in computer ...
research
05/30/2022

Knowledge Distillation for 6D Pose Estimation by Keypoint Distribution Alignment

Knowledge distillation facilitates the training of a compact student net...
research
07/29/2023

Effective Whole-body Pose Estimation with Two-stages Distillation

Whole-body pose estimation localizes the human body, hand, face, and foo...
research
03/21/2023

Heterogeneous-Branch Collaborative Learning for Dialogue Generation

With the development of deep learning, advanced dialogue generation meth...
research
03/18/2023

Crowd Counting with Online Knowledge Learning

Efficient crowd counting models are urgently required for the applicatio...

Please sign up or login with your details

Forgot password? Click here to reset