FGPNet: A weakly supervised fine-grained 3D point clouds classification network

doi:10.1016/j.patcog.2023.109509

2023-07-01

PRE

白静 (Jing Bai) *

Hongbo Liang

DOI：10.1016/j.patcog.2023.109509

原文链接

原文求助

摘要

En 中文

3D point clouds classification has been a hot research topic and received great progress in recent years. However, due to the similar data distributions and subtle differences among various sub-categories in a meta-category, the 3D point clouds classification at a fine-grained level is still very challenging, especially without the annotations of part locations or attributes. In this paper, we propose a novel weakly super -vised network for fine-grained 3D point clouds classification, namely FGPNet. Different from the previous supervised fine-grained classification methods that use class labels and other manual annotation infor-mation, FGPNet develops a unified framework to address both local geometric details and global spatial structures only using the class labels as input. Specifically, FGPNet firstly employs a context-aware dis-criminative feature extraction (CDFE) module, which extract contextual contrasted information across dif-ferential receptive fields hierarchically, and further capture discriminative local details from point clouds. Subsequently, an SimAM-Capsule Aggregation (SCA) module is introduced to highlight the significant lo -cal features and capture their spatial relationships. Quantitative and qualitative experimental results on fine-grained dataset including three categories Airplane, Chair and Car demonstrate that FGPNet outper-forms the state-of-the-art methods on fine-grained 3D point clouds classification tasks.(c) 2023 Elsevier Ltd. All rights reserved.

Keyword:

3D point clouds

Fine-grained classification

Context-aware feature extraction

SimAM-Capsule aggregation

Local geometric details

Spatial relationships