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.
翻译:自我监督学习(SSL)是一种从未贴标签的数据中学习有用表达方式的技术,已经有效地应用于图像和视频的域适应(DA),在3D感知问题中,它是否以及如何被利用来进行域适应,目前还不清楚。在这里,我们描述了用于DA的关于点云的SSL的首次研究。我们引入了一套新的借口任务,即变形重建,这是在Sim-to-Real转换中遇到的变形的启发下进行的。此外,我们提出了一个新的培训程序,用于根据称为点云混合(PCM)的MixUp方法,进行贴标签的点云数据。对用于分类和分解的域适应数据集的评估显示现有方法和基线方法的巨大改进。