Improving Performance of the PRYSTINE Traffic Sign Classification by Using a Perturbation-Based Explainability Approach

Improving Performance of the PRYSTINE Traffic Sign Classification by Using a Perturbation-Based Explainability Approach

Model understanding is critical in many domains, particularly those involved in high-stakes decisions, e.g., medicine, criminal justice, and autonomous driving. Explainable AI (XAI) methods are essential for working with black-box models such as convolutional neural networks. This paper evaluates th...

Full description

Bibliographic Details
Main Authors: Kaspars Sudars, Ivars Namatēvs, Kaspars Ozols
Format: Article
Language:English
Published: MDPI AG 2022-01-01
Series:Journal of Imaging
Subjects:
explainable AI
convolutional neural network
network compression
Online Access:https://www.mdpi.com/2313-433X/8/2/30

Similar Items

Similar Items