Structured Context Enhancement Network for Mouse Pose Estimation

TL;DR

This paper introduces GM-SCENet, a novel deep learning model with structured context modules for accurate mouse pose estimation, addressing challenges posed by mouse deformability and body part motion differences.

Contribution

The paper proposes GM-SCENet with Structured Context Mixer and Cascaded Multi-Level Supervision modules, improving mouse pose estimation accuracy over existing methods.

Findings

Enhanced keypoint localization accuracy in mouse pose estimation.

Robustness of the model across different mouse postures.

Outperforms baseline methods in experimental evaluations.

Abstract

Automated analysis of mouse behaviours is crucial for many applications in neuroscience. However, quantifying mouse behaviours from videos or images remains a challenging problem, where pose estimation plays an important role in describing mouse behaviours. Although deep learning based methods have made promising advances in human pose estimation, they cannot be directly applied to pose estimation of mice due to different physiological natures. Particularly, since mouse body is highly deformable, it is a challenge to accurately locate different keypoints on the mouse body. In this paper, we propose a novel Hourglass network based model, namely Graphical Model based Structured Context Enhancement Network (GM-SCENet) where two effective modules, i.e., Structured Context Mixer (SCM) and Cascaded Multi-Level Supervision (CMLS) are subsequently implemented. SCM can adaptively learn and enhance the proposed structured context information of each mouse part by a novel graphical model that takes into account the motion difference between body parts. Then, the CMLS module is designed to jointly train the proposed SCM and the Hourglass network by generating multi-level information, increasing the robustness of the whole network.Using the multi-level prediction information from SCM and CMLS, we develop an inference method to ensure the accuracy of the localisation results. Finally, we evaluate our proposed approach against several baselines...