Visualizing Point Cloud Classifiers by Curvature Smoothing
This work addresses the need for interpretability in point cloud classification networks, offering a tool for diagnosing and improving architectures, though it is incremental as it builds on existing visualization techniques.
The paper tackles the problem of understanding point cloud classifiers by proposing a visualization method based on curvature smoothing, which identifies important features by smoothing curved areas and evaluating classification changes, with results providing insights into various classifiers.
Recently, several networks that operate directly on point clouds have been proposed. There is significant utility in understanding their mechanisms to classify point clouds, which can potentially help diagnosing these networks and designing better architectures. In this paper, we propose a novel approach to visualize features important to the point cloud classifiers. Our approach is based on smoothing curved areas on a point cloud. After prominent features were smoothed, the resulting point cloud can be evaluated on the network to assess whether the feature is important to the classifier. A technical contribution of the paper is an approximated curvature smoothing algorithm, which can smoothly transition from the original point cloud to one of constant curvature, such as a uniform sphere. Based on the smoothing algorithm, we propose PCI-GOS (Point Cloud Integrated-Gradients Optimized Saliency), a visualization technique that can automatically find the minimal saliency map that covers the most important features on a shape. Experiment results revealed insights into different point cloud classifiers.