Uncertainty-aware Prototype Learning with Variational Inference for Few-shot Point Cloud Segmentation

TL;DR

This paper introduces UPL, a probabilistic framework for few-shot 3D segmentation that models uncertainty in prototypes using variational inference, leading to improved robustness and interpretability.

Contribution

It proposes a novel uncertainty-aware prototype learning method with a dual-stream refinement and variational inference formulation for few-shot 3D segmentation.

Findings

Achieves state-of-the-art results on ScanNet and S3DIS benchmarks.

Provides reliable uncertainty estimation alongside segmentation.

Enhances robustness and generalization in few-shot 3D segmentation.

Abstract

Few-shot 3D semantic segmentation aims to generate accurate semantic masks for query point clouds with only a few annotated support examples. Existing prototype-based methods typically construct compact and deterministic prototypes from the support set to guide query segmentation. However, such rigid representations are unable to capture the intrinsic uncertainty introduced by scarce supervision, which often results in degraded robustness and limited generalization. In this work, we propose UPL (Uncertainty-aware Prototype Learning), a probabilistic approach designed to incorporate uncertainty modeling into prototype learning for few-shot 3D segmentation. Our framework introduces two key components. First, UPL introduces a dual-stream prototype refinement module that enriches prototype representations by jointly leveraging limited information from both support and query samples. Second, we formulate prototype learning as a variational inference problem, regarding class prototypes as latent variables. This probabilistic formulation enables explicit uncertainty modeling, providing robust and interpretable mask predictions. Extensive experiments on the widely used ScanNet and S3DIS benchmarks show that our UPL achieves consistent state-of-the-art performance under different settings while providing reliable uncertainty estimation. The code is available at https://fdueblab-upl.github.io/.