ICML 2021spotlight19 citations

Unsupervised Co-part Segmentation through Assembly

Qingzhe Gao, Bin Wang, Libin Liu, Baoquan Chen

Abstract

Co-part segmentation is an important problem in computer vision for its rich applications. We propose an unsupervised learning approach for co-part segmentation from images. For the training stage, we leverage motion information embedded in videos and explicitly extract latent representations to segment meaningful object parts. More importantly, we introduce a dual procedure of part-assembly to form a closed loop with part-segmentation, enabling an effective self-supervision. We demonstrate the effectiveness of our approach with a host of extensive experiments, ranging from human bodies, hands, quadruped, and robot arms. We show that our approach can achieve meaningful and compact part segmentation, outperforming state-of-the-art approaches on diverse benchmarks.

BibTeX
@InProceedings{pmlr-v139-gao21c,
  title = 	 {Unsupervised Co-part Segmentation through Assembly},
  author =       {Gao, Qingzhe and Wang, Bin and Liu, Libin and Chen, Baoquan},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {3576--3586},
  year = 	 {2021},
  editor = 	 {Meila, Marina and Zhang, Tong},
  volume = 	 {139},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {18--24 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v139/gao21c/gao21c.pdf},
  url = 	 {https://proceedings.mlr.press/v139/gao21c.html},
  abstract = 	 {Co-part segmentation is an important problem in computer vision for its rich applications. We propose an unsupervised learning approach for co-part segmentation from images. For the training stage, we leverage motion information embedded in videos and explicitly extract latent representations to segment meaningful object parts. More importantly, we introduce a dual procedure of part-assembly to form a closed loop with part-segmentation, enabling an effective self-supervision. We demonstrate the effectiveness of our approach with a host of extensive experiments, ranging from human bodies, hands, quadruped, and robot arms. We show that our approach can achieve meaningful and compact part segmentation, outperforming state-of-the-art approaches on diverse benchmarks.}
}