Self-Supervised Learning for Domain Adaptation on Point-Clouds. (arXiv:2003.12641v5 [cs.CV] UPDATED)

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 …

arxiv cv domain adaptation learning self-supervised learning supervised learning