Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation

TL;DR

This paper introduces a semi-supervised learning method for 3D point cloud segmentation that leverages unlabeled data through a guided contrastive loss, improving model performance and addressing class imbalance.

Contribution

The paper proposes a novel guided point contrastive loss with pseudo-label guidance and confidence filtering for semi-supervised 3D segmentation.

Findings

Significant performance improvements on ScanNet V2, S3DIS, and SemanticKITTI datasets.

Effective mitigation of class imbalance through category-balanced sampling.

Enhanced feature representation and generalization in semi-supervised learning.

Abstract

Rapid progress in 3D semantic segmentation is inseparable from the advances of deep network models, which highly rely on large-scale annotated data for training. To address the high cost and challenges of 3D point-level labeling, we present a method for semi-supervised point cloud semantic segmentation to adopt unlabeled point clouds in training to boost the model performance. Inspired by the recent contrastive loss in self-supervised tasks, we propose the guided point contrastive loss to enhance the feature representation and model generalization ability in semi-supervised setting. Semantic predictions on unlabeled point clouds serve as pseudo-label guidance in our loss to avoid negative pairs in the same category. Also, we design the confidence guidance to ensure high-quality feature learning. Besides, a category-balanced sampling strategy is proposed to collect positive and negative samples to mitigate the class imbalance problem. Extensive experiments on three datasets (ScanNet V2, S3DIS, and SemanticKITTI) show the effectiveness of our semi-supervised method to improve the prediction quality with unlabeled data.