Label-Efficient Learning on Point Clouds Using Approximate Convex Decompositions
Abstract
The problems of shape classification and part segmentation from 3D point clouds have garnered increasing attention in the last few years. Both of these problems, however, suffer from relatively small training sets, creating the need for statistically efficient methods to learn 3D shape representations. In this paper, we investigate the use of Approximate Convex Decompositions (ACD) as a self-supervisory signal for label-efficient learning of point cloud representations. We show that using ACD to approximate ground truth segmentation provides excellent self-supervision for learning 3D point cloud representations that are highly effective on downstream tasks. We report improvements over the state-of-the-art for unsupervised representation learning on the ModelNet40 shape classification dataset and significant gains in few-shot part segmentation on the ShapeNetPart dataset. Our source code is publicly available.
Cite
Text
Gadelha et al. "Label-Efficient Learning on Point Clouds Using Approximate Convex Decompositions." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58607-2_28Markdown
[Gadelha et al. "Label-Efficient Learning on Point Clouds Using Approximate Convex Decompositions." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/gadelha2020eccv-labelefficient/) doi:10.1007/978-3-030-58607-2_28BibTeX
@inproceedings{gadelha2020eccv-labelefficient,
title = {{Label-Efficient Learning on Point Clouds Using Approximate Convex Decompositions}},
author = {Gadelha, Matheus and RoyChowdhury, Aruni and Sharma, Gopal and Kalogerakis, Evangelos and Cao, Liangliang and Learned-Miller, Erik and Wang, Rui and Maji, Subhransu},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2020},
doi = {10.1007/978-3-030-58607-2_28},
url = {https://mlanthology.org/eccv/2020/gadelha2020eccv-labelefficient/}
}