$\hbox {C}^2$DFL: cross-view cross-layer discriminative feature learning for fine-grained 3D shape classification

期刊论文
发表日期：

2025年3月22日

查看全文

Jinzhe Jiang,
Jing Bai,
Xiangyu Ma

摘要

Fine-grained 3D shape classification poses challenges in effectively capturing and integrating discriminative features residing in subtle local regions. Previous methods typically extract features independently from individual views of 3D shapes, with a focus on various strategies for fusing these extracted view features. However, this approach neglects interview correlations and potential redundancies among different views. In this study, we introduce $\hbox {C}^2$ $C^{2}$ DFL, which consists of two primary modules: cross-view discriminative feature extraction (CV-DFE) and cross-layer discriminative feature fusion (CL-DFF). CV-DFE integrates discriminative features by merging inputs from multiple views, mitigating limitations associated with isolated feature extraction. CL-DFF dynamically selects key tokens using a transformer model to interactively fuse discriminative features from various levels. Extensive experiments conducted on three categories of the FG3D dataset demonstrate the exceptional efficacy of $\hbox {C}^2$ $C^{2}$ DFL in capturing and integrating discriminative features of 3D shapes. The proposed method achieves state-of-the-art accuracy in fine-grained 3D shape classification (FGSC).

\(\hbox {C}^2\)DFL: cross-view cross-layer discriminative feature learning for fine-grained 3D shape classification

摘要