Surrogate Model-Based Explainability Methods for Point Cloud NNs
This addresses the need for interpretable AI in autonomous driving and robotics, where point clouds are critical, but it is incremental as it builds on existing surrogate model techniques.
The paper tackles the lack of explainability methods for point cloud neural networks by proposing a local surrogate model-based approach to identify components contributing to classification, and it introduces quantitative fidelity validations to enhance explanation persuasiveness and compare existing methods, showing fairly accurate and semantically coherent results.
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 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