论文标题
使用近似凸面分解对点云上的标签有效学习
Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions
论文作者
论文摘要
在过去几年中，形状分类和部分分割的问题引起了人们的关注。但是，这两个问题都遭受了相对较小的训练集，因此需要统计上有效的方法来学习3D形状表示。在本文中，我们研究了近似凸分解（ACD）作为一种自我探索信号，用于对点云表示的标签学习。我们表明，使用ACD近似地面真理分段为学习在下游任务上非常有效的3D点云表示提供了出色的自我划分。我们报告了对ModelNet40形状分类数据集的无监督表示学习的最先进的改进，并在shapenetpart dataset上的几个零件分割中的显着收益。
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.Code available at https://github.com/matheusgadelha/PointCloudLearningACD
