论文标题
使用基于梯度的可视化来解释点云的深层神经网络
Explaining Deep Neural Networks for Point Clouds using Gradient-based Visualisations
论文作者
论文摘要
解释深层神经网络做出的决定是一个快速发展的研究主题。近年来，几种方法试图提供有关为结构化2D图像输入数据设计的神经网络做出决定的视觉解释。在本文中，我们提出了一种新颖的方法，以生成旨在对非结构化3D数据（即点云）进行分类的网络的粗略视觉解释。我们的方法使用流回到最终特征图层的梯度并将这些值映射为输入点云中相应点的贡献。由于维数分歧和输入点和最终特征图之间缺乏空间一致性，我们的方法将梯度与点下降相结合以计算点云的不同部分的解释。我们的方法的一般性在各种点云分类网络上进行了测试，包括“单一对象”网络PointNet，PointNet ++，DGCNN和“场景”网络投票。我们的方法生成对称解释图，该图突出显示了重要区域，并提供了对网络体系结构决策过程的见解。我们对使用定量，定量和人类研究的比较方法对解释方法的信任和解释性进行了详尽的评估。我们所有的代码均在Pytorch中实施，并将公开使用。
Explaining decisions made by deep neural networks is a rapidly advancing research topic. In recent years, several approaches have attempted to provide visual explanations of decisions made by neural networks designed for structured 2D image input data. In this paper, we propose a novel approach to generate coarse visual explanations of networks designed to classify unstructured 3D data, namely point clouds. Our method uses gradients flowing back to the final feature map layers and maps these values as contributions of the corresponding points in the input point cloud. Due to dimensionality disagreement and lack of spatial consistency between input points and final feature maps, our approach combines gradients with points dropping to compute explanations of different parts of the point cloud iteratively. The generality of our approach is tested on various point cloud classification networks, including 'single object' networks PointNet, PointNet++, DGCNN, and a 'scene' network VoteNet. Our method generates symmetric explanation maps that highlight important regions and provide insight into the decision-making process of network architectures. We perform an exhaustive evaluation of trust and interpretability of our explanation method against comparative approaches using quantitative, quantitative and human studies. All our code is implemented in PyTorch and will be made publicly available.
