loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Chenkai Zhang ; Daisuke Deguchi ; Jialei Chen and Hiroshi Murase

Affiliation: Graduate School of Informatics, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, 464–8601, Japan

Keyword(s): Autonomous Driving, Convolutional Neural Network, End-to-End Model, Explainability.

Abstract: Deep learning technology has rapidly advanced, leading to the development of End-to-End driving models (E2EDMs) for autonomous vehicles with high prediction accuracy. To comprehend the prediction results of these E2EDMs, one of the most representative explanation methods is attribution-based. There are two kinds of attribution-based explanation methods: pixel-level and object-level. Usually, the heatmaps illustrate the importance of pixels and objects in the prediction results, serving as explanations for E2EDMs. Since there are many attribution-based explanation methods, evaluation methods are proposed to determine which one is better at improving the explainability of E2EDMs. Fidelity measures the explanation’s faithfulness to the model’s prediction method, which is a bottommost property. However, no evaluation method could measure the fidelity difference between object-level and pixel-level explanations, making the current evaluation incomplete. In addition, without considering fi delity, previous evaluation methods may advertise manipulative explanations that solely seek human satisfaction (persuasibility). Therefore, we propose an evaluation method that further considers fidelity, our method enables a comprehensive evaluation that proves the object-level explanations genuinely outperform pixel-level explanations in fidelity and persuasibility, thus could better improve the explainability of the E2EDMs. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.191.103.144

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Zhang, C.; Deguchi, D.; Chen, J. and Murase, H. (2024). Comprehensive Evaluation of End-to-End Driving Model Explanations for Autonomous Vehicles. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8; ISSN 2184-4321, SciTePress, pages 509-518. DOI: 10.5220/0012365900003660

@conference{visapp24,
author={Chenkai Zhang. and Daisuke Deguchi. and Jialei Chen. and Hiroshi Murase.},
title={Comprehensive Evaluation of End-to-End Driving Model Explanations for Autonomous Vehicles},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={509-518},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012365900003660},
isbn={978-989-758-679-8},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Comprehensive Evaluation of End-to-End Driving Model Explanations for Autonomous Vehicles
SN - 978-989-758-679-8
IS - 2184-4321
AU - Zhang, C.
AU - Deguchi, D.
AU - Chen, J.
AU - Murase, H.
PY - 2024
SP - 509
EP - 518
DO - 10.5220/0012365900003660
PB - SciTePress