AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimation
This work addresses the lack of AI methods for infant pose estimation, which is crucial for early detection of neurodevelopmental disorders, but it is incremental as it builds on existing transformer-based approaches.
The paper tackles infant pose estimation by proposing a new dataset and a Deep Aggregation Vision Transformer (AggPose), which improves performance by 0.8 AP on COCO and outperforms existing models like HRFormer and TokenPose on the infant dataset.
Movement and pose assessment of newborns lets experienced pediatricians predict neurodevelopmental disorders, allowing early intervention for related diseases. However, most of the newest AI approaches for human pose estimation methods focus on adults, lacking publicly benchmark for infant pose estimation. In this paper, we fill this gap by proposing infant pose dataset and Deep Aggregation Vision Transformer for human pose estimation, which introduces a fast trained full transformer framework without using convolution operations to extract features in the early stages. It generalizes Transformer + MLP to high-resolution deep layer aggregation within feature maps, thus enabling information fusion between different vision levels. We pre-train AggPose on COCO pose dataset and apply it on our newly released large-scale infant pose estimation dataset. The results show that AggPose could effectively learn the multi-scale features among different resolutions and significantly improve the performance of infant pose estimation. We show that AggPose outperforms hybrid model HRFormer and TokenPose in the infant pose estimation dataset. Moreover, our AggPose outperforms HRFormer by 0.8 AP on COCO val pose estimation on average. Our code is available at github.com/SZAR-LAB/AggPose.