OccAM's Laser: Occlusion-Based Attribution Maps for 3D Object Detectors on LiDAR Data

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Abstract

While 3D object detection in LiDAR point clouds is well-established in academia and industry, the explainability of these models is a largely unexplored field. In this paper, we propose a method to generate attribution maps for the detected objects in order to better understand the behavior of such models. These maps indicate the importance of each 3D point in predicting the specific objects. Our method works with black-box models: We do not require any prior knowledge of the architecture nor access to the model’s internals, like parameters, activations or gradients. Our efficient perturbation-based approach empirically estimates the importance of each point by testing the model with randomly generated subsets of the input point cloud. Our sub-sampling strategy takes into account the special characteristics of LiDAR data, such as the depth-dependent point density. We show a detailed evaluation of the attribution maps and demonstrate that they are interpretable and highly informative. Furthermore, we compare the attribution maps of recent 3D object detection architectures to provide insights into their decision-making processes.
Original languageEnglish
Title of host publicationProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
Pages1131-1140
Number of pages10
ISBN (Electronic)9781665469463
DOIs
Publication statusPublished - 2022
Event2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition: CVPR 2022 - New Orleans Ernest N. Morial Convention Center, Hybrider Event, New Orleans, United States
Duration: 21 Jun 202224 Sept 2022
Conference number: 2022

Conference

Conference2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Abbreviated titleCVPR 2022
Country/TerritoryUnited States
CityHybrider Event, New Orleans
Period21/06/2224/09/22

Keywords

  • 3D from multi-view and sensors
  • categorization
  • Deep learning architectures and techniques
  • Explainable computer vision
  • Navigation and autonomous driving
  • Recognition: detection
  • retrieval
  • Robot vision

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'OccAM's Laser: Occlusion-Based Attribution Maps for 3D Object Detectors on LiDAR Data'. Together they form a unique fingerprint.

Cite this