Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning

Abstract

Point clouds have attracted increasing attention. Significant progress has been made in methods for point cloud analysis, which often requires costly human annotation as supervision. To address this issue, we propose a novel self-contrastive learning for self-supervised point cloud representation learning, aiming to capture both local geometric patterns and nonlocal semantic primitives based on the nonlocal self-similarity of point clouds. The contributions are two-fold: on the one hand, instead of contrasting among different point clouds as commonly employed in contrastive learning, we exploit self-similar point cloud patches within a single point cloud as positive samples and otherwise negative ones to facilitate the task of contrastive learning. On the other hand, we actively learn hard negative samples that are close to positive samples for discriminative feature learning. Experimental results show that the proposed method achieves state-of-the-art performance on widely used benchmark datasets for self-supervised point cloud segmentation and transfer learning for classification.

Accepted to ACM MM 2021

References in corpus (12)

• Semi-Supervised Classification with Graph Convolutional Networks
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Learning Representations by Maximizing Mutual Information Across Views
• AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data
• Self-Supervised Deep Learning on Point Clouds by Reconstructing Space
• Conditional Negative Sampling for Contrastive Learning of Visual Representations
• MortonNet: Self-Supervised Learning of Local Features in 3D Point Clouds
• A Polynomial-time Solution for Robust Registration with Extreme Outlier Rates
• Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations
• SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences
• AVT: Unsupervised Learning of Transformation Equivariant Representations by Autoencoding Variational Transformations