FGPNet: A weakly supervised fine-grained 3D point clouds classification network. (July 2023)

• Record Type: Journal Article
• Authors: Shao, Huihui; Bai, Jing; Wu, Rusong; Jiang, Jinzhe; Liang, Hongbo
• Is Part Of: Pattern recognition. Volume 139(2023)
• Publication Date: 2023-07
• Subjects: 3D point clouds -- Fine-grained classification -- Context-aware feature extraction -- SimAM-Capsule aggregation -- Local geometric details -- Spatial relationships; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2023.109509
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: In view of the necessity and research value, we are the first to specialize in studying fine-grained classification under the 3D point clouds representation, providing a new perspective for 3D shape classification. Through in-depth analysis of the characteristics of the target object (3D point clouds) and the key to fine-grained classification tasks, design a feature extraction model to effectively learn the discriminative features. To highlight discriminative local regions and captures spatial differences between 3D point clouds from different sub-categories, propose a module to capture spatial structure feature and aggerate local features. Abstract: 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 supervised 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 information, 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 discriminative feature extraction (CDFE) module, which extract contextual contrasted information across differential 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 local 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 outperforms the state-of-the-art methods on fine-grained 3D point clouds classification tasks.