Anti-drift pose tracker (ADPT), a transformer-based network for robust animal pose estimation cross-species.

Journal: eLife
PMID:

Abstract

Deep learning-based methods have advanced animal pose estimation, enhancing accuracy, and efficiency in quantifying animal behavior. However, these methods frequently experience tracking drift, where noise-induced jumps in body point estimates compromise reliability. Here, we present the anti-drift pose tracker (ADPT), a transformer-based tool that mitigates tracking drift in behavioral analysis. Extensive experiments across cross-species datasets-including proprietary mouse and monkey recordings and public and macaque datasets-demonstrate that ADPT significantly reduces drift and surpasses existing models like DeepLabCut and SLEAP in accuracy. Moreover, ADPT achieved 93.16% identification accuracy for 10 unmarked mice and 90.36% accuracy for freely interacting unmarked mice, which can be further refined to 99.72%, enhancing both anti-drift performance and pose estimation accuracy in social interactions. With its end-to-end design, ADPT is computationally efficient and suitable for real-time analysis, offering a robust solution for reproducible animal behavior studies. The ADPT code is available at https://github.com/tangguoling/ADPT.

Authors

  • Guoling Tang
    University of Chinese Academy of Sciences, Shenzhen, China.
  • Yaning Han
    University of Chinese Academy of Sciences, Shenzhen, China.
  • Xing Sun
    1 Division of Life Science, Applied Genomics Centre and Centre for Statistical Science, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong, P. R. China.
  • Ruonan Zhang
    Department of Radiology, The First Affiliated Hospital, Sun Yat-Sen University, 58 Zhongshan II Road, Guangzhou, 510080, Guangdong, People's Republic of China.
  • Ming-Hu Han
    University of Chinese Academy of Sciences, Shenzhen, China.
  • Quanying Liu
    Shenzhen Key Laboratory of Smart Healthcare Engineering, Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen 518055, China. Electronic address: liuqy@sustech.edu.cn.
  • Pengfei Wei
    School of Computing, National University of Singapore, Singapore. Electronic address: dcsweip@nus.edu.sg.