Learn to Learn Metric Space for Few-Shot Segmentation of 3D Shapes

TL;DR

This paper introduces a meta-learning approach for few-shot 3D shape segmentation that learns a specialized metric space to classify shape parts with minimal labeled data, outperforming existing methods.

Contribution

It proposes a novel meta-metric learning framework that dynamically adapts to new classes for 3D shape segmentation with few labeled examples.

Findings

Outperforms baseline and semi-supervised methods on ShapeNet dataset

Effective in few-shot scenarios with limited labeled data

Demonstrates superior generalization to unseen classes

Abstract

Recent research has seen numerous supervised learning-based methods for 3D shape segmentation and remarkable performance has been achieved on various benchmark datasets. These supervised methods require a large amount of annotated data to train deep neural networks to ensure the generalization ability on the unseen test set. In this paper, we introduce a meta-learning-based method for few-shot 3D shape segmentation where only a few labeled samples are provided for the unseen classes. To achieve this, we treat the shape segmentation as a point labeling problem in the metric space. Specifically, we first design a meta-metric learner to transform input shapes into embedding space and our model learns to learn a proper metric space for each object class based on point embeddings. Then, for each class, we design a metric learner to extract part-specific prototype representations from a few support shapes and our model performs per-point segmentation over the query shapes by matching each point to its nearest prototype in the learned metric space. A metric-based loss function is used to dynamically modify distances between point embeddings thus maximizes in-part similarity while minimizing inter-part similarity. A dual segmentation branch is adopted to make full use of the support information and implicitly encourages consistency between the support and query prototypes. We demonstrate the superior performance of our proposed on the ShapeNet part dataset under the few-shot scenario, compared with well-established baseline and state-of-the-art semi-supervised methods.