论文标题
可视化点云DNN的全局解释
Visualizing Global Explanations of Point Cloud DNNs
论文作者
论文摘要
在自动驾驶和机器人技术领域，点云显示出其出色的实时性能，作为来自大多数主流3D传感器的原始数据。因此，近年来，点云神经网络已成为流行的研究方向。但是，到目前为止，关于点云的深神经网络的解释性很少。在本文中，我们根据基于局部替代模型的方法提出了一种可点云的可解释性方法，以显示哪些组件有助于分类。此外，我们为生成的解释提出了定量的保真度验证，以增强解释性的有说服力，并比较不同现有点云可解释性方法的合理性。我们的新解释性方法为点云分类任务提供了一种相当准确，更具语义上的连贯性和广泛适用的解释。我们的代码可在https://github.com/explain3d/lime-3d上找到
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
