In recent years, research on few-shot learning (FSL) has been fast-growing in the 2D image domain due to the less requirement for labeled training data and greater generalization for novel classes. However, its application in 3D point cloud data is relatively under-explored. Not only need to distinguish unseen classes as in the 2D domain, 3D FSL is more challenging in terms of irregular structures, subtle inter-class differences, and high intra-class variances {when trained on a low number of data.} Moreover, different architectures and learning algorithms make it difficult to study the effectiveness of existing 2D FSL algorithms when migrating to the 3D domain. In this work, for the first time, we perform systematic and extensive investigations of directly applying recent 2D FSL works to 3D point cloud related backbone networks and thus suggest a strong learning baseline for few-shot 3D point cloud classification. Furthermore, we propose a new network, Point-cloud Correlation Interaction (PCIA), with three novel plug-and-play components called Salient-Part Fusion (SPF) module, Self-Channel Interaction Plus (SCI+) module, and Cross-Instance Fusion Plus (CIF+) module to obtain more representative embeddings and improve the feature distinction. These modules can be inserted into most FSL algorithms with minor changes and significantly improve the performance. Experimental results on three benchmark datasets, ModelNet40-FS, ShapeNet70-FS, and ScanObjectNN-FS, demonstrate that our method achieves state-of-the-art performance for the 3D FSL task. Code and datasets are available at https://github.com/cgye96/A_Closer_Look_At_3DFSL.

翻译：近年来，由于对标注训练数据需求较少且对新颖类别具有更强泛化能力，二维图像领域的少样本学习研究发展迅速。然而，其在三维点云数据中的应用相对未充分探索。与二维领域类似，少样本三维点云分类不仅需要区分未见类别，还面临不规则结构、类别间细微差异以及训练数据量少时高类内方差等更具挑战性的问题。此外，不同架构和学习方法使得研究现有二维少样本学习算法迁移至三维领域时的有效性变得困难。在本工作中，我们首次系统且广泛地研究了将近期二维少样本学习工作直接应用于三维点云相关骨干网络的方法，从而为少样本三维点云分类提出了一个强学习基线。此外，我们提出了一个新网络——点云关联交互网络（Point-cloud Correlation Interaction, PCIA），其中包含三个新型即插即用组件：显著部分融合模块（Salient-Part Fusion, SPF）、自通道交互增强模块（Self-Channel Interaction Plus, SCI+）和跨实例融合增强模块（Cross-Instance Fusion Plus, CIF+），以获取更具代表性的嵌入并提升特征区分性。这些模块可通过微小改动嵌入大多数少样本学习算法，并显著提升性能。在三个基准数据集ModelNet40-FS、ShapeNet70-FS和ScanObjectNN-FS上的实验结果表明，我们的方法在三维少样本学习任务中达到了最先进水平。代码和数据集可在https://github.com/cgye96/A_Closer_Look_At_3DFSL获取。