用谱聚类选3D点云原型，高效持续学习
Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection
- 用谱聚类从点云中挑选每类代表性原型
- 模型网40和谢普纳数据集上超越现有方法
- 内存占用仅为对手一半，适合资源受限场景
我们提出一种用于3D物体分类的持续学习新框架CL3D，基于谱聚类选择每类原型。针对非欧几里得数据如点云，只要定义样本间距离度量，即可利用3D几何特性识别代表性原型。我们探索了在输入空间（3D点）、局部特征空间（1024维）和全局特征空间中的聚类效果。在ModelNet40、ShapeNet和ScanNet数据集上实验表明，仅使用输入空间特征即达到当前最优准确率；结合输入、局部与全局特征后，在ModelNet40和ShapeNet上进一步提升性能，且内存消耗仅为竞争方法的一半。在挑战性强的ScanNet数据集上，准确率提升4.1%，内存仅需对手的28%，展现方法的良好可扩展性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。