International Journal of Automotive Engineering
Online ISSN : 2185-0992
Print ISSN : 2185-0984
ISSN-L : 2185-0992
Research Paper
Reliability Evaluation of Visualization Performance of Convolutional Neural Network Models for Automated Driving
Chenkai ZhangYuki OkafujiTakahiro Wada
Author information

2021 Volume 12 Issue 2 Pages 41-47


As deep learning methods in image recognition have achieved excellent performance, researchers have begun to apply CNNs(convolutional neural networks) to automated driving. However, the explainability for the decision making of automated driving is highly desired. In order to trust the model in automated driving, visualization methods have become important for understanding the internal calculation process of CNNs. Therefore, in a previous study, we proposed a method to evaluate the visualization performance of CNN models by using a mathematical model instead of a human driver to generate a dataset that can determine the ground-truth point in images. However, the reliability of the proposed method for validating the visualization performance was not provided. Therefore, in this paper, we verify the proposed method through two experiments to demonstrate the task-dependent performance and visualization performance during training. The reliability of the visualization performance has been demonstrated through experimental results. Therefore, we proposed an evaluation method for visualization performance in automated driving systems.

Content from these authors
© 2021 Society of Automotive Engineers of Japan, Inc

This article is licensed under a Creative Commons [Attribution-NonCommercial-ShareAlike 4.0 International] license.
Previous article Next article