1. [Publications](/publications)
2. Self-Supervised Learning for Domain Adaptation on Point-Clouds
 
 # Self-Supervised Learning for Domain Adaptation on Point-Clouds

  ![](/sites/default/files/styles/wide/public/publications/img_2.png?itok=G2Aj1xxU)

 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.



 ## Authors



Idan Achituve (Bar-Ilan University)

[Haggai Maron](/person/haggai-maron)

[Gal Chechik](/person/gal-chechik)

 

 

 ## Publication Date



Saturday, January 9, 2021

 

 ## Published in



[Winter Conference on Applications of Computer Vision (WACV), 2021](https://arxiv.org/pdf/2003.12641.pdf)

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

[Computer Vision](/research-area/computer-vision)