CLR-GAM: Contrastive Point Cloud Learning with Guided Augmentation and Feature Mapping
This work addresses the challenge of efficient self-supervised learning for point clouds in robotics and self-driving, offering incremental improvements over existing contrastive methods.
The paper tackles the problem of learning discriminative 3D point cloud representations without annotations by introducing CLR-GAM, a contrastive learning framework with guided augmentation and feature mapping, which achieves state-of-the-art performance on classification, few-shot learning, and segmentation tasks across simulated and real-world datasets.
Point cloud data plays an essential role in robotics and self-driving applications. Yet, annotating point cloud data is time-consuming and nontrivial while they enable learning discriminative 3D representations that empower downstream tasks, such as classification and segmentation. Recently, contrastive learning-based frameworks have shown promising results for learning 3D representations in a self-supervised manner. However, existing contrastive learning methods cannot precisely encode and associate structural features and search the higher dimensional augmentation space efficiently. In this paper, we present CLR-GAM, a novel contrastive learning-based framework with Guided Augmentation (GA) for efficient dynamic exploration strategy and Guided Feature Mapping (GFM) for similar structural feature association between augmented point clouds. We empirically demonstrate that the proposed approach achieves state-of-the-art performance on both simulated and real-world 3D point cloud datasets for three different downstream tasks, i.e., 3D point cloud classification, few-shot learning, and object part segmentation.