Real-Time Incremental Explanations for Object Detectors in Autonomous Driving

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Calderón-Peña, Santiago, Chockler, Hana, Kelly, David A.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910863150022656
author Calderón-Peña, Santiago
Chockler, Hana
Kelly, David A.
author_facet Calderón-Peña, Santiago
Chockler, Hana
Kelly, David A.
contents Object detectors are widely used in safety-critical real-time applications such as autonomous driving. Explainability is especially important for safety-critical applications, and due to the variety of object detectors and their often proprietary nature, black-box explainability tools are needed. However, existing black-box explainability tools for AI models rely on multiple model calls, rendering them impractical for real-time use. In this paper, we introduce IncX, an algorithm and a tool for real-time black-box explainability for object detectors. The algorithm is based on linear transformations of saliency maps, producing sufficient explanations. We evaluate our implementation on four widely used video datasets of autonomous driving and demonstrate that IncX's explanations are comparable in quality to the state-of-the-art and are computed two orders of magnitude faster than the state-of-the-art, making them usable in real time.
format Preprint
id arxiv_https___arxiv_org_abs_2408_11963
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Real-Time Incremental Explanations for Object Detectors in Autonomous Driving
Calderón-Peña, Santiago
Chockler, Hana
Kelly, David A.
Computer Vision and Pattern Recognition
Artificial Intelligence
Object detectors are widely used in safety-critical real-time applications such as autonomous driving. Explainability is especially important for safety-critical applications, and due to the variety of object detectors and their often proprietary nature, black-box explainability tools are needed. However, existing black-box explainability tools for AI models rely on multiple model calls, rendering them impractical for real-time use. In this paper, we introduce IncX, an algorithm and a tool for real-time black-box explainability for object detectors. The algorithm is based on linear transformations of saliency maps, producing sufficient explanations. We evaluate our implementation on four widely used video datasets of autonomous driving and demonstrate that IncX's explanations are comparable in quality to the state-of-the-art and are computed two orders of magnitude faster than the state-of-the-art, making them usable in real time.
title Real-Time Incremental Explanations for Object Detectors in Autonomous Driving
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2408.11963