论文标题
对点云的域适应域的自我监督学习
Self-Supervised Learning for Domain Adaptation on Point-Clouds
论文作者
论文摘要
自我监督学习（SSL）是一种从未标记的数据学习有用表示的技术。它已有效地应用于图像和视频的域适应（DA）。在3D感知问题中，是否以及如何利用域的适应性来利用它以及如何利用它。在这里，我们描述了在点云上DA的SSL的首次研究。我们介绍了一个新的借口任务，变形重构，灵感来自SIM到真实转换中遇到的变形。此外，我们提出了一个新颖的训练程序，用于由称为Point Cloud Mixup（PCM）的混合方法动机的标记点云数据。对域改编数据集进行分类和分割的评估，证明了对现有和基线方法的大量改进。
Self-supervised learning (SSL) is a technique for learning useful representations from unlabeled data. It has been applied effectively to domain adaptation (DA) on images and videos. It is still unknown if and how it can be leveraged for domain adaptation in 3D perception problems. Here we describe the first study of SSL for DA on point clouds. We introduce a new family of pretext tasks, Deformation Reconstruction, inspired by the deformations encountered in sim-to-real transformations. In addition, we propose a novel training procedure for labeled point cloud data motivated by the MixUp method called Point cloud Mixup (PCM). Evaluations on domain adaptations datasets for classification and segmentation, demonstrate a large improvement over existing and baseline methods.
