Point cloud data, a flexible 3D object representation, is critical for various applications such as autonomous driving, robotics and remote sensing. Despite the recent success of deep neural networks (DNNs) on supervised point cloud analysis tasks, they still rely on tedious manual annotation of point clouds and cannot make predictions for new classes. Unlike few-shot learning for 2D images with the advantages of large-scale datasets and high-quality deep pre-trained models like ResNet, for 3D few-shot learning, obtaining discriminative representations of unseen classes with high intra-class similarity and inter-class difference is very challenging. To address this issue, this work proposes a novel cascade graph neural network for few-shot learning on point clouds, termed as CGNN, in which two cascade GNNs are adopted to extract the intra-object topological information and learn the inter-object relations respectively. To further increase the discriminability of point cloud features, we first design a novel discriminative edge label to model the intra-class similarity and inter-class dissimilarity based on channel-wise feature variance and class consistency. Second, we propose a novel few-shot circle loss which classifies the nodes into two subsets, i.e., support to support pairs and support to query pairs, and optimizes the pair-wise similarity on two subsets independently. Extensive experiments on benchmark CAD and real LiDAR point cloud datasets have demonstrated that CGNN improves accuracy by 5.98% over the state-of-the-art GNN-based few-shot classification methods.
Cascade Graph Neural Networks for Few-Shot Learning on Point Clouds
IEEE Transactions on Intelligent Transportation Systems ; 24 , 8 ; 8788-8798
2023-08-01
2958619 byte
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
One-shot Imitation Learning with Graph Neural Networks for Pick-and-Place Manipulation Tasks
BASE | 2023
|Graph based over-segmentation methods for 3D point clouds
British Library Online Contents | 2018
|Learning Semantics on Radar Point-Clouds
IEEE | 2021
|SOLUTIONS - Information Sciences - Cascade Error-Projection Learning in Neural Networks
Online Contents | 2001