Human pose estimation with 80% smaller model and 68% less CPU using STNet
Human pose estimation with %80 smaller model and 68% less CPU using STNet
Towards Simple and Accurate Human Pose Estimation with Stair Network
arXiv paper abstract https://arxiv.org/abs/2202.09115v1
arXiv PDF paper https://arxiv.org/pdf/2202.09115v1.pdf
In … keypoint coordinates regression task. … existing approaches adopt complicated networks with a large number of parameters, leading to a heavy model with poor cost-effectiveness in practice.
… To overcome … develop a small yet discrimicative model called STair Network, which can be simply stacked towards an accurate multi-stage pose estimation system.
… composed of novel basic feature extraction blocks which focus on promoting feature diversity and obtaining rich local representations with fewer parameters
… introduce two mechanisms with negligible computational cost, focusing on feature fusion and replenish.
… 1-stage STair Network … higher accuracy than HRNet by 5.5% on COCO test dataset with 80% fewer parameters and 68% fewer GFLOPs.
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
