Mapper-GIN: Lightweight Structural Graph Abstraction for Corrupted 3D Point Cloud Classification
This addresses the problem of corruption robustness in 3D point cloud classification for computer vision applications, offering an efficient and interpretable alternative to heavier methods.
The paper tackled robust 3D point cloud classification by proposing Mapper-GIN, a lightweight pipeline that uses structural graph abstraction instead of scaling up models or data augmentation. It achieved competitive accuracy on the ModelNet40-C corruption benchmark with only 0.5M parameters, demonstrating stable performance under noise and transformation corruptions.
Robust 3D point cloud classification is often pursued by scaling up backbones or relying on specialized data augmentation. We instead ask whether structural abstraction alone can improve robustness, and study a simple topology-inspired decomposition based on the Mapper algorithm. We propose Mapper-GIN, a lightweight pipeline that partitions a point cloud into overlapping regions using Mapper (PCA lens, cubical cover, and followed by density-based clustering), constructs a region graph from their overlaps, and performs graph classification with a Graph Isomorphism Network. On the corruption benchmark ModelNet40-C, Mapper-GIN achieves competitive and stable accuracy under Noise and Transformation corruptions with only 0.5M parameters. In contrast to prior approaches that require heavier architectures or additional mechanisms to gain robustness, Mapper-GIN attains strong corruption robustness through simple region-level graph abstraction and GIN message passing. Overall, our results suggest that region-graph structure offers an efficient and interpretable source of robustness for 3D visual recognition.