LiDAR-based 3D object detection has made impressive progress recently, yet most existing models are black-box, lacking interpretability. Previous explanation approaches primarily focus on analyzing image-based models and are not readily applicable to LiDAR-based 3D detectors. In this paper, we propose a feature factorization activation map (FFAM) to generate high-quality visual explanations for 3D detectors. FFAM employs non-negative matrix factorization to generate concept activation maps and subsequently aggregates these maps to obtain a global visual explanation. To achieve object-specific visual explanations, we refine the global visual explanation using the feature gradient of a target object. Additionally, we introduce a voxel upsampling strategy to align the scale between the activation map and input point cloud. We qualitatively and quantitatively analyze FFAM with multiple detectors on several datasets. Experimental results validate the high-quality visual explanations produced by FFAM. The Code will be available at \url{https://github.com/Say2L/FFAM.git}.

翻译：基于激光雷达的3D目标检测近期取得了显著进展，但现有模型大多为黑箱模型，缺乏可解释性。以往的解释方法主要聚焦于分析基于图像的模型，难以直接应用于基于激光雷达的3D检测器。本文提出了一种特征分解激活图（FFAM），用于生成3D检测器的高质量视觉解释。FFAM采用非负矩阵分解生成概念激活图，随后聚合这些图以获得全局视觉解释。为实现特定目标的视觉解释，我们利用目标对象的特征梯度对全局视觉解释进行精炼。此外，我们引入了一种体素上采样策略，以对齐激活图与输入点云之间的尺度。我们在多个数据集上对FFAM与多种检测器进行了定性和定量分析。实验结果验证了FFAM所生成的高质量视觉解释。代码将开源在 \url{https://github.com/Say2L/FFAM.git}。