BriefGPT.xyz
Mar, 2020
点云领域自适应的自监督学习
Self-Supervised Learning for Domain Adaptation on Point-Clouds
HTML
PDF
Idan Achituve, Haggai Maron, Gal Chechik
TL;DR
本篇论文探究了自监督学习在3D感知问题的领域自适应中的应用，通过提出基于形变重构的预训练任务以及一种名为PCM的新颖训练流程，对分类和分割的领域适应数据集进行了评估，取得了相较于现有和基准方法的巨大改进。
Abstract
self-supervised learning
(SSL) allows to learn useful representations from unlabeled data and has been applied effectively for
domain adaptation
(DA) on images. It is still unknown if and how it can be leveraged
→