Few-Shot Point Cloud Semantic Segmentation via Contrastive Self-Supervision and Multi-Resolution Attention

TL;DR

This paper introduces a contrastive self-supervision framework combined with multi-resolution attention for few-shot point cloud semantic segmentation, effectively reducing feature bias and improving generalization to unseen classes.

Contribution

The paper proposes a novel class-agnostic contrastive pretraining method and a multi-resolution attention module for enhanced few-shot point cloud segmentation.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Effectively reduces feature extraction bias for unseen classes.

Demonstrates practical effectiveness in CAM/CAD segmentation applications.

Abstract

This paper presents an effective few-shot point cloud semantic segmentation approach for real-world applications. Existing few-shot segmentation methods on point cloud heavily rely on the fully-supervised pretrain with large annotated datasets, which causes the learned feature extraction bias to those pretrained classes. However, as the purpose of few-shot learning is to handle unknown/unseen classes, such class-specific feature extraction in pretrain is not ideal to generalize into new classes for few-shot learning. Moreover, point cloud datasets hardly have a large number of classes due to the annotation difficulty. To address these issues, we propose a contrastive self-supervision framework for few-shot learning pretrain, which aims to eliminate the feature extraction bias through class-agnostic contrastive supervision. Specifically, we implement a novel contrastive learning approach with a learnable augmentor for a 3D point cloud to achieve point-wise differentiation, so that to enhance the pretrain with managed overfitting through the self-supervision. Furthermore, we develop a multi-resolution attention module using both the nearest and farthest points to extract the local and global point information more effectively, and a center-concentrated multi-prototype is adopted to mitigate the intra-class sparsity. Comprehensive experiments are conducted to evaluate the proposed approach, which shows our approach achieves state-of-the-art performance. Moreover, a case study on practical CAM/CAD segmentation is presented to demonstrate the effectiveness of our approach for real-world applications.