# FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors

arXiv: https://arxiv.org/abs/2405.12601 · HTML: https://mlsanity.com/paper/2405.12601/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 41 references that are in the map.
- First posted on arXiv 21 May 2024.

## Builds on (most cited first, 30 of 31)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection](https://mlsanity.com/paper/2012.15712/) (2020)
- [Real Time Image Saliency for Black Box Classifiers](https://mlsanity.com/paper/1705.07857/) (2017)
- [VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking](https://mlsanity.com/paper/2303.11301/) (2023)
- [Full-Gradient Representation for Neural Network Visualization](https://mlsanity.com/paper/1905.00780/) (2019)
- [DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets](https://mlsanity.com/paper/2301.06051/) (2023)
- [PointCloud Saliency Maps](https://mlsanity.com/paper/1812.01687/) (2018)
- [Black-box Explanation of Object Detectors via Saliency Maps](https://mlsanity.com/paper/2006.03204/) (2020)
- [Deep Feature Factorization For Concept Discovery](https://mlsanity.com/paper/1806.10206/) (2018)
- [Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1908.02686/) (2019)
- [HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/2310.20234/) (2023)
- [Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks](https://mlsanity.com/paper/1712.06302/) (2017)
- [3D Point Cloud Feature Explanations Using Gradient-Based Methods](https://mlsanity.com/paper/2006.05548/) (2020)
- [OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data](https://mlsanity.com/paper/2204.06577/) (2022)
- [ODAM: Gradient-based instance-specific visual explanations for object detection](https://mlsanity.com/paper/2304.06354/) (2023)
- [Visualizing Global Explanations of Point Cloud DNNs](https://mlsanity.com/paper/2203.09505/) (2022)
- [G-CAME: Gaussian-Class Activation Mapping Explainer for Object Detectors](https://mlsanity.com/paper/2306.03400/) (2023)

## Built on by (most cited first, 2 of 2)

- [InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory](https://mlsanity.com/paper/2505.19820/) (2025)
- [VGER: Voxel-Guided Global Event Ranking for Event Cloud Attribution](https://mlsanity.com/paper/2608.01470/) (2026)

## Abstract (arXiv)

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 urlhttps://github.com/Say2L/FFAM.git.