Work

Explainable Artificial Intelligence for Object Detection in the Automotive Sector

Year: 2025

Type: conference-paper

Abstract: In the automotive domain, object detection is pivotal for enhancing safety and autonomy through the identification of various objects of interest. However, insights into the influential image pixels in the detection process are often lacking. Recognizing these significant regions within the image not only enriches our qualitative understanding of the model’s functionality but also empowers us to refine and optimize its performance. Employing Explainable Artificial Intelligence (XAI), we present an XAI component in this paper. This component explains the predictions made by a pre-trained object detection model for a given image by generating heatmaps that highlight the most critical regions in the image for the detected objects.

DOI: 10.3390/engproc2025107044

Authors: Marios Siganos, Panagiotis Radoglou-Grammatikis, Thomas Lagkas, Vasileios Argyriou, Sotirios Goudos, Konstantinos Psannis, Konstantinos-Filippos Kollias, George Fragulis, Panagiotis Sarigiannidis

Institutions: K3Y Ltd (Bulgaria), University of Western Macedonia, Democritus University of Thrace, Kingston University London, Aristotle University of Thessaloniki, University of Macedonia

Language: English

Topic: Explainable Artificial Intelligence (XAI)

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Funder: European Commission

OpenAlex ID: W4413880343

FWCI:

Cites: 11

Cited by:

Related to: 10