Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions
Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions
复制标题
DOI：
10.1007/978-3-030-58607-2_28
复制
发表时间：
2020-03
期刊：
影响因子：
--
通讯作者：
Matheus Gadelha;Aruni RoyChowdhury;Gopal Sharma;E. Kalogerakis;Liangliang Cao;E. Learned-Miller;Rui Wang;Subhransu Maji
中科院分区：
文献类型：
--
作者：
Matheus Gadelha;Aruni RoyChowdhury;Gopal Sharma;E. Kalogerakis;Liangliang Cao;E. Learned-Miller;Rui Wang;Subhransu Maji
从三维点云数据中进行形状分类和零件分割的问题在过去的几年中得到了越来越多的关注。然而，这两个问题都受到相对较小的训练集的影响，需要统计有效的方法来学习3D形状表示。在本文中，我们研究了使用近似凸分解（ACD）作为一个自监督信号的标签有效的学习点云表示。我们表明，使用ACD近似地面实况分割提供了良好的自我监督学习3D点云表示，是非常有效的下游任务。我们报告了在ModelNet40形状分类数据集上进行无监督表示学习的最新技术水平的改进，以及在ShapeNetPart数据集上进行少镜头部分分割的显著收益。我们的源代码是公开的（ https://github.com/matheusgadelha/PointCloudLearningACD ).
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 ( https://github.com/matheusgadelha/PointCloudLearningACD ).