TransPose: Keypoint Localization via Transformer
Preprint
Abstract
While CNN-based models have made remarkable progress on human pose estimation, what spatial dependencies they capture to localize keypoints remains unclear. In this work, we propose a model called \textbf{TransPose}, which introduces Transformer for human pose estimation. The attention layers built in Transformer enable our model to capture long-range relationships efficiently and also can reveal what dependencies the predicted keypoints rely on. To predict keypoint heatmaps, the last attention layer acts as an aggregator, which collects contributions from image clues and forms maximum positions of keypoints. Such a heatmap-based localization approach via Transformer conforms to the principle of Activation Maximization~\cite{erhan2009visualizing}. And the revealed dependencies are image-specific and fine-grained, which also can provide evidence of how the model handles special cases, e.g., occlusion. The experiments show that TransPose achieves 75.8 AP and 75.0 AP on COCO validation and test-dev sets, while being more lightweight and faster than mainstream CNN architectures. The TransPose model also transfers very well on MPII benchmark, achieving superior performance on the test set when fine-tuned with small training costs. Code and pre-trained models are publicly available\footnote{\url{https://github.com/yangsenius/TransPose}}.Keywords
All Related Versions
This publication has 38 references indexed in Scilit:
- Learning Delicate Local Representations for Multi-person Pose Estimation2020
- Hand-Transformer: Non-Autoregressive Structured Modeling for 3D Hand Pose Estimation2020
- End-to-End Object Detection with Transformers2020
- PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model2018
- Simple Baselines for Human Pose Estimation and Tracking2018
- Integral Human Pose Regression2018
- Top-Down Neural Attention by Excitation Backprop2016
- Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural NetworkInternational Journal of Computer Vision, 2014
- Pose Machines: Articulated Pose Estimation via Inference Machines2014
- Microsoft COCO: Common Objects in Context2014