Unsupervised Contrastive Learning with Simple Transformation for 3D Point Cloud Data

TL;DR

This paper introduces a simple unsupervised contrastive learning method for 3D point cloud data using a transformation to generate positive pairs, improving performance on classification and segmentation tasks.

Contribution

It proposes a novel transformation-based contrastive learning approach for unsupervised 3D point cloud representation learning, outperforming existing methods.

Findings

Outperforms current unsupervised methods in classification and segmentation

Achieves comparable results to supervised methods

Effective on multiple downstream 3D tasks

Abstract

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. By contrast, unsupervised learning of point cloud data has received much less attention to date. In this paper, we propose a simple yet effective approach for unsupervised point cloud learning. In particular, we identify a very useful transformation which generates a good contrastive version of an original point cloud. They make up a pair. 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. To demonstrate the efficacy of our method, we 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). Comprehensive results show that our unsupervised contrastive representation learning enables impressive outcomes in object classification and semantic segmentation. It generally outperforms current unsupervised methods, and even achieves comparable performance to supervised methods. Our source codes will be made publicly available.