Semi-supervised 2D Human Pose Estimation via Adaptive Keypoint Masking

arXiv:2404.14835v1 Announce Type: new
Abstract: Human pose estimation is a fundamental and challenging task in computer vision. Larger-scale and more accurate keypoint annotations, while helpful for improving the accuracy of supervised pose estimation, are often expensive and difficult to obtain. Semi-supervised pose estimation tries to leverage a large amount of unlabeled data to improve model performance, which can alleviate the problem of insufficient labeled samples. The latest semi-supervised learning usually adopts a strong and weak data augmented teacher-student learning framework …

abstract accuracy annotations arxiv computer computer vision cs.cv fundamental human improving masking scale semi-supervised type via vision