Visualizing Global Explanations of Point Cloud DNNs

TL;DR

This paper introduces a new explainability method for point cloud neural networks, providing accurate, semantically coherent explanations for classifications, validated through quantitative fidelity measures and comparison with existing methods.

Contribution

It presents a novel local surrogate model-based explainability approach tailored for point cloud DNNs, with validation techniques and comparative analysis.

Findings

Provides accurate and semantically coherent explanations.

Enhances explainability validation with quantitative fidelity measures.

Outperforms existing point cloud explainability methods.

Abstract

In the field of autonomous driving and robotics, point clouds are showing their excellent real-time performance as raw data from most of the mainstream 3D sensors. Therefore, point cloud neural networks have become a popular research direction in recent years. So far, however, there has been little discussion about the explainability of deep neural networks for point clouds. In this paper, we propose a point cloud-applicable explainability approach based on a local surrogate model-based method to show which components contribute to the classification. Moreover, we propose quantitative fidelity validations for generated explanations that enhance the persuasive power of explainability and compare the plausibility of different existing point cloud-applicable explainability methods. Our new explainability approach provides a fairly accurate, more semantically coherent and widely applicable explanation for point cloud classification tasks. Our code is available at https://github.com/Explain3D/LIME-3D