Get human pose using attention mechanism to expand receptive fields with SADI-NET
Get human pose using attention mechanism to expand receptive fields with SADI-NET
Spatial Attention-based Distribution Integration Network for Human Pose Estimation
arXiv paper abstract https://arxiv.org/abs/2311.05323
arXiv PDF paper https://arxiv.org/pdf/2311.05323.pdf
… human pose estimation … face limitations … with challenging scenarios, including occlusion, diverse appearances, variations in illumination, and overlap … present the Spatial Attention-based Distribution Integration Network (SADI-NET) to improve the accuracy
… network consists of three efficient models: the receptive fortified module (RFM), spatial fusion module (SFM), and distribution learning module (DLM).
Building upon … HourglassNet architecture, … replace the basic block with … proposed RFM. The RFM incorporates a dilated residual block and attention mechanism to expand receptive fields while enhancing sensitivity to spatial information.
In addition, the SFM incorporates multi-scale characteristics by employing both global and local attention mechanisms.
Furthermore, the DLM, inspired by residual log-likelihood estimation (RLE), reconfigures a predicted heatmap using a trainable distribution weight.
… model … demonstrating significant improvements over existing models and establishing state-of-the-art performance.
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
