GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation
This addresses the challenge of large computational overhead in human pose estimation for industrial applications, though it is incremental as it builds on Transformer-based approaches.
The paper tackles the problem of efficient human pose estimation, especially for whole-body with numerous keypoints, by proposing GTPT, which achieves higher performance with less computation compared to other methods on COCO and COCO-WholeBody benchmarks.
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.