Unsupervised Co-part Segmentation through Assembly

Qingzhe Gao, Bin Wang, Libin Liu, Baoquan Chen
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3576-3586, 2021.

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.

Cite this Paper

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.} }
Endnote
%0 Conference Paper %T Unsupervised Co-part Segmentation through Assembly %A Qingzhe Gao %A Bin Wang %A Libin Liu %A Baoquan Chen %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-gao21c %I PMLR %P 3576--3586 %U https://proceedings.mlr.press/v139/gao21c.html %V 139 %X 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.
APA
Gao, Q., Wang, B., Liu, L. & Chen, B.. (2021). Unsupervised Co-part Segmentation through Assembly. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:3576-3586 Available from https://proceedings.mlr.press/v139/gao21c.html.

Related Material