Abstract
Accurate lightweight pose estimation is still a difficult challenging task influenced by different human poses and various complex backgrounds in 2D human images. To address the above problems, we propose a Lightweight Single-branch Pose Distillation network, termed LSPD, which is a lightweight powerful fully convolutional pose network that can be executed quickly with a low computational cost for accurate pose estimation. First, we introduced an efficient end-to-end pose distillation sequence framework, which utilizes a small number of lightweight and strong pose estimation stages to effectively transfer the pose knowledge of our teacher model. Second, we constructed a compact and strong pose estimation stage that uses a type of lightweight multi-scale residual block to enhance the image features and the image-dependent spatial features representation ability of the model. At the same time, it reduces the computational cost. Finally, when training is complete, we used the backbone network and the first student stage as the simple architecture to deploy. Extensive experiments demonstrated that the proposed method obtains excellent performance with high accuracy and low model parameters.
Funding Information
  • Natural Science Foundation of Guangxi (2019GXNSFDA185006, 2019GXNSFDA185007)
  • National Natural Science Foundation of China (62262006)
  • Guilin Science and Technology Development Program (20210104-1)
  • Guangxi Key Research and Development Program (AB17195053, AD18281002)