GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation
Preprint
Abstract
In recent years, 2D human pose estimation has made significant progress on public benchmarks. However, many of these approaches face challenges of less applicability in the industrial community due to the large number of parametric quantities and computational overhead. Efficient human pose estimation remains a hurdle, especially for whole-body pose estimation with numerous keypoints. While most current methods for efficient human pose estimation primarily rely on CNNs, we propose the Group-based Token Pruning Transformer (GTPT) that fully harnesses the advantages of the Transformer. GTPT alleviates the computational burden by gradually introducing keypoints in a coarse-to-fine manner. It minimizes the computation overhead while ensuring high performance. Besides, GTPT groups keypoint tokens and prunes visual tokens to improve model performance while reducing redundancy. We propose the Multi-Head Group Attention (MHGA) between different groups to achieve global interaction with little computational overhead. We conducted experiments on COCO and COCO-WholeBody. Compared to other methods, the experimental results show that GTPT can achieve higher performance with less computation, especially in whole-body with numerous keypoints.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- 2D Human pose estimation: a surveyMultimedia Systems, 2022
- ZoomNAS: Searching for Whole-body Human Pose Estimation in the WildIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- ARFDNet: An efficient activity recognition & fall detection system using latent feature poolingKnowledge-Based Systems, 2022
- DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders2021
- Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation2021
- Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows2021
- EventHPE: Event-based 3D Human Pose and Shape Estimation2021
- TokenPose: Learning Keypoint Tokens for Human Pose Estimation2021
- OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity FieldsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- Microsoft COCO: Common Objects in Context2014