From Pose to Part: Weakly-Supervised Pose Evolution for Human Part Segmentation
Lists
Only you see this
Abstract
Human part segmentation is a crucial but challenging task in computer vision. Recent works have achieved progress with the help of pixel-wise annotations. However, annotating pixel-wise masks especially at part-level is a tedious and labor-intensive procedure. To overcome this problem, we propose a part evolution framework to learn reliable predictions from weak pose annotations, which are much easier to collect. Our framework is composed of two essential modules: the first part adaptation module is designed to learn the deep prior knowledge from three related tasks, i.e., pose estimation, part-level and object-level segmentation; the second module is the part evolution module, which refines the part priors from deep predictions with the boundary-aware optimization algorithm. These two modules are conducted iteratively to evolve pose keypoint annotations into reliable part priors. Experimental evidence shows that our weakly-supervised approach generates comparable results with the state-of-the-art strongly-supervised methods on public benchmarks, and also validates the potential of notable improvements when combining weak labels with existing part segmentation masks.
BibTeX
@article{zhao2023from,
author = {Yifan Zhao and Jia Li and Yu Zhang and Yonghong Tian},
title = {{From Pose to Part: Weakly-Supervised Pose Evolution for Human Part Segmentation}},
journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
year = {2023},
url = {https://openreview.net/forum?id=DqJxXzUyAX},
}Loading related content...