Efficient Pose Estimation via a Lightweight Single-Branch Pose Distillation Network

Abstract

Accurate lightweight (LW) pose estimation is still a challenging task influenced by different human poses and various complex backgrounds in 2-D 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 multiscale 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.