Task-Adaptive Channel Attention Graph Network for Few-Shot 3D Point Cloud Classification

Few-shot 3D point cloud classification remains a challenging task due to the irregular geometry and sparse nature of point clouds, coupled with the scarcity of labeled data. Existing methods often rely on task-agnostic feature extractors, limiting their ability to adapt low-level features to novel tasks effectively. To address this limitation, we propose a Task-adaptive Channel Attention Graph Network (TCAGN), a novel framework that dynamically adapts feature extraction to both instance-specific and task-aware contexts. TCAGN extends the widely used DGCNN backbone by integrating two attention mechanisms: Instance Channel Attention Module (ICAM), which emphasizes semantically meaningful channels for individual instances, and Task-adaptive Channel Attention Module (TCAM), which generates task-specific channel attention for all features within a task. These two modules are hierarchically integrated into each EdgeConv block, enabling progressive feature refinement tailored to the unique characteristics of each few-shot task. We evaluate TCAGN on three benchmark datasets, ModelNet40-FS, ShapeNet70-FS, and ScanObjectNN-FS, demonstrating state-of-the-art performance with improvements of 1.1%–2.7% over existing methods. Ablation studies indicate that the combination of ICAM and TCAM contributes 3.0%–6.2% of the overall performance gain.