arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.18210cs.CV
收藏

深入探讨少样本3D点云分类

A Closer Look at Few-Shot 3D Point Cloud Classification

Shanghai AI Laboratory(上海人工智能实验室);Fudan University(复旦大学);Institute for Infocomm Research, A*STAR(新加坡科技研究局资讯通信研究院)

Chuangguan Ye, Hongyuan Zhu, Bo Zhang, Tao Chen

AI总结:

本文系统评估了2D少样本学习算法在3D点云上的迁移效果,并提出包含三个即插即用模块的PCIA网络,显著提升了3D点云少样本分类的性能。

摘要:

近年来,由于对标注训练数据的需求较少且对新颖类别具有更强的泛化能力,2D图像领域的少样本学习(FSL)研究发展迅速。然而,其在3D点云数据中的应用却相对缺乏探索。3D FSL不仅需要像2D领域那样区分未见过的类别,而且在数据量较少的情况下训练时,由于不规则结构、细微的类间差异和较大的类内方差,其挑战性更大。此外,不同的架构和学习算法使得研究现有2D FSL算法迁移到3D领域时的有效性变得困难。在本研究中,我们首次将近期2D FSL工作直接应用于3D点云相关的骨干网络,进行了系统且广泛的调查,从而为少样本3D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Point-cloud Correlation Interaction(PCIA),包含三个新颖的即插即用组件:Salient-Part Fusion(SPF)模块、Self-Channel Interaction Plus(SCI+)模块和Cross-Instance Fusion Plus(CIF+)模块,以获取更具代表性的嵌入并改善特征区分度。这些模块只需微小改动即可插入大多数FSL算法中,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3D FSL任务上实现了最先进的性能。代码和数据集可在 https://github.com/cgye96/A_Closer_Look_At_3DFSL 获取。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑