Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learning

TL;DR

This paper introduces a novel weakly supervised 3D point cloud segmentation method using a multi-prototype classifier that effectively captures intra-class variations and discovers semantic subclasses without extra annotations.

Contribution

It proposes a multi-prototype classifier with constraints for updating prototypes, addressing intra-class variation in weakly supervised segmentation.

Findings

Effective in low-label regimes

Discovers semantic subclasses without extra labels

Validates approach through experiments

Abstract

Addressing the annotation challenge in 3D Point Cloud segmentation has inspired research into weakly supervised learning. Existing approaches mainly focus on exploiting manifold and pseudo-labeling to make use of large unlabeled data points. A fundamental challenge here lies in the large intra-class variations of local geometric structure, resulting in subclasses within a semantic class. In this work, we leverage this intuition and opt for maintaining an individual classifier for each subclass. Technically, we design a multi-prototype classifier, each prototype serves as the classifier weights for one subclass. To enable effective updating of multi-prototype classifier weights, we propose two constraints respectively for updating the prototypes w.r.t. all point features and for encouraging the learning of diverse prototypes. Experiments on weakly supervised 3D point cloud segmentation tasks validate the efficacy of proposed method in particular at low-label regime. Our hypothesis is also verified given the consistent discovery of semantic subclasses at no cost of additional annotations.