Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection

TL;DR

This paper presents CL3D, a spectral clustering-based framework for continual learning in 3D point cloud classification, achieving state-of-the-art results with reduced memory usage by selecting representative prototypes.

Contribution

The paper introduces a novel spectral clustering approach for exemplar selection in continual learning on 3D point clouds, leveraging geometric features for improved efficiency and accuracy.

Findings

Achieved state-of-the-art accuracy on ModelNet40 and ShapeNet datasets.

Improved ScanNet accuracy by 4.1% with 72% less memory.

Effectively used input, local, and global features for clustering.

Abstract

We introduce a novel framework for Continual Learning in 3D object classification. Our approach, CL3D, is based on the selection of prototypes from each class using spectral clustering. For non-Euclidean data such as point clouds, spectral clustering can be employed as long as one can define a distance measure between pairs of samples. Choosing the appropriate distance measure enables us to leverage 3D geometric characteristics to identify representative prototypes for each class. We explore the effectiveness of clustering in the input space (3D points), local feature space (1024-dimensional points), and global feature space. We conduct experiments on the ModelNet40, ShapeNet, and ScanNet datasets, achieving state-of-the-art accuracy exclusively through the use of input space features. By leveraging the combined input, local, and global features, we have improved the state-of-the-art on ModelNet and ShapeNet, utilizing nearly half the memory used by competing approaches. For the challenging ScanNet dataset, our method enhances accuracy by 4.1% while consuming just 28% of the memory used by our competitors, demonstrating the scalability of our approach.