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

Abstract

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.

arXiv commentAccepted by IJCV 2023

References in corpus (13)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• ShapeNet: An Information-Rich 3D Model Repository
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• Meta-Learning for Semi-Supervised Few-Shot Classification
• Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
• SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
• CrossTransformers: spatially-aware few-shot transfer
• Self-Supervised Few-Shot Learning on Point Clouds
• H-CNN: Spatial Hashing Based CNN for 3D Shape Analysis
• Channel Importance Matters in Few-Shot Image Classification
• What Makes for Effective Few-shot Point Cloud Classification?

Cited by in corpus (2)

• AllSpark: A Multimodal Spatio-Temporal General Intelligence Model with Ten Modalities via Language as a Reference Framework
• Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation