Visualizing Global Explanations of Point Cloud DNNs
This work addresses the explainability problem for researchers and practitioners in autonomous driving and robotics using point cloud data, representing an incremental improvement by adapting existing methods to a new domain.
The paper tackles the lack of explainability methods for point cloud deep neural networks by proposing a local surrogate model-based approach to identify components contributing to classification, with results showing fairly accurate and semantically coherent explanations validated through quantitative fidelity measures.
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