Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation

no code implementations • CVPR 2023 • Zhehan Kan, Shuoshuo Chen, Ce Zhang, Yushun Tang, Zhihai He

This strong correlation suggests that we can use this error as feedback to guide the correction process.

Pose Estimation

Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation

no code implementations • CVPR 2023 • Yushun Tang, Ce Zhang, Heng Xu, Shuoshuo Chen, Jie Cheng, Luziwei Leng, Qinghai Guo, Zhihai He

We observe that the performance of this feed-forward Hebbian learning for fully test-time adaptation can be significantly improved by incorporating a feedback neuro-modulation layer.

Test-time Adaptation

Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation

no code implementations • 6 Jul 2022 • Zhehan Kan, Shuoshuo Chen, Zeng Li, Zhihai He

This group-wise structural correlation can be explored to improve the accuracy and robustness of human pose estimation.

Inference Optimization Multi-Person Pose Estimation +1