Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation

Zhehan Kan; Shuoshuo Chen; Ce Zhang; Yushun Tang; Zhihai He

10.1109/CVPR52729.2023.00536

2023

1063-6919

979-8-3503-0130-4

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

5537-5546

17-24 June 2023

Vancouver, BC, Canada

A central challenge in human pose estimation, as well as in many other machine learning and prediction tasks, is the generalization problem. The learned network does not have the capability to characterize the prediction error, generate feedback information from the test sample, and correct the prediction error on the fly for each individual test sample, which results in degraded performance in generalization. In this work, we introduce a self-correctable and adaptable inference (SCAI) method to address the generalization challenge of network prediction and use human pose estimation as an example to demonstrate its effectiveness and performance. We learn a correction network to correct the prediction result conditioned by a fitness feedback error. This feedback error is generated by a learned fitness feedback network which maps the prediction result to the original input domain and compares it against the original input. Interestingly, we find that this self-referential feedback error is highly correlated with the actual prediction error. This strong correlation suggests that we can use this error as feedback to guide the correction process. It can be also used as a loss function to quickly adapt and optimize the correction network during the inference process. Our extensive experimental results on human pose estimation demonstrate that the proposed SCAI method is able to significantly improve the generalization capability and performance of human pose estimation.

Humans: Face body pose gesture movement

第一

CPCI-S

WOS:001058542605084

IEEE

Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China

Zhehan Kan,Shuoshuo Chen,Ce Zhang,et al. Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation[C],2023:5537-5546.