Point cloud analysis with unsupervised learning using simple contrastive learning with Jiang

Point cloud analysis with unsupervised learning using simple contrastive learning with Jiang

Unsupervised Contrastive Learning with Simple Transformation for 3D Point Cloud Data
arXiv paper abstract https://arxiv.org/abs/2110.06632
arXiv PDF paper https://arxiv.org/pdf/2110.06632.pdf

Though a number of point cloud learning methods have been proposed to handle unordered points, most of them are supervised and require labels for training.

… propose a simple yet effective approach for unsupervised point cloud learning.

… identify a very useful transformation which generates a good contrastive version of an original point cloud.

… After going through a shared encoder and a shared head network, the consistency between the output representations are maximized with introducing two variants of contrastive losses to respectively facilitate downstream classification and segmentation.

… conduct experiments on three downstream tasks which are 3D object classification (on ModelNet40 and ModelNet10), shape part segmentation (on ShapeNet Part dataset) as well as scene segmentation (on S3DIS).

… unsupervised contrastive representation learning … in object classification and semantic segmentation … generally outperforms current unsupervised methods, and even achieves comparable performance to supervised methods …

Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website

LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b

Photo by Flipsnack on Unsplash