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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Shuai, Li, Boyang, Fang, Zhiyu, Cui, Mingyue, Huang, Kai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916254183325696
author Liu, Shuai
Li, Boyang
Fang, Zhiyu
Cui, Mingyue
Huang, Kai
author_facet Liu, Shuai
Li, Boyang
Fang, Zhiyu
Cui, Mingyue
Huang, Kai
contents 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}.
format Preprint
id arxiv_https___arxiv_org_abs_2405_12601
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors
Liu, Shuai
Li, Boyang
Fang, Zhiyu
Cui, Mingyue
Huang, Kai
Computer Vision and Pattern Recognition
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}.
title FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.12601