English

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

Computer Vision and Pattern Recognition 2023-02-22 v1

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.

Keywords

Cite

@article{arxiv.2302.10501,
  title  = {Few-Shot Point Cloud Semantic Segmentation via Contrastive Self-Supervision and Multi-Resolution Attention},
  author = {Jiahui Wang and Haiyue Zhu and Haoren Guo and Abdullah Al Mamun and Cheng Xiang and Tong Heng Lee},
  journal= {arXiv preprint arXiv:2302.10501},
  year   = {2023}
}

Comments

ICRA 2023

R2 v1 2026-06-28T08:45:19.685Z