The Library
SAFE: Saliency-Aware Counterfactual Explanations for DNN-based automated driving systems
Tools
Samadi, Amir, Shirian, Amir, Koufos, Konstantinos, Debattista, Kurt and Dianati, Mehrdad (2023) SAFE: Saliency-Aware Counterfactual Explanations for DNN-based automated driving systems. In: 26th IEEE International Conference on Intelligent Transportation Systems (ITSC 2023), Bilbao, Bizkaia, Spain, 24-28 Sep 2023 (In Press)
|
PDF
WRAP-SAFE-Saliency-aware-counterfactual-explanations-DNN-automated-driving-systems-23.pdf - Accepted Version - Requires a PDF viewer. Download (2991Kb) | Preview |
Abstract
The explainability of Deep Neural Networks (DNNs) has recently gained significant importance especially in safety-critical applications such as automated/autonomous vehicles, a.k.a. automated driving systems. CounterFactual (CF) explanations have emerged as a promising approach for interpreting the behaviour of black-box DNNs. A CF explainer identifies the minimum modifications in the input that would alter the model’s output to its complement. In other words, a CF explainer computes the minimum modifications required to cross the model’s
decision boundary. Current deep generative CF models often work with user-selected features rather than focusing on the discriminative features of the black-box model. Consequently, such CF examples may not necessarily lie near the decision boundary, thereby contradicting the definition of CFs. To address this issue, we propose in this paper a novel approach that leverages saliency maps to generate more informative CF
explanations. Our approach guides a Generative Adversarial Network based on the most influential features of the input of the black-box model to produce CFs near the decision boundary. We evaluate the performance of this approach using a real-world dataset of driving scenes, BDD100k, and demonstrate its superiority over several baseline methods in
terms of well-known CF metrics, including proximity, sparsity and validity. Our work contributes to the ongoing efforts to improve the interpretability of DNNs and provides a promising direction for generating more accurate and informative CF explanations
Item Type: | Conference Item (Paper) | ||||||
---|---|---|---|---|---|---|---|
Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software T Technology > TL Motor vehicles. Aeronautics. Astronautics |
||||||
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > Engineering | ||||||
Library of Congress Subject Headings (LCSH): | Automated vehicles, Vehicular ad hoc networks (Computer networks), Neural networks (Computer science), Counterfactuals (Logic), Decision making -- Data processing, Automotive event data recorders | ||||||
Publisher: | IEEE | ||||||
Official Date: | 24 September 2023 | ||||||
Dates: |
|
||||||
Status: | Peer Reviewed | ||||||
Publication Status: | In Press | ||||||
Reuse Statement (publisher, data, author rights): | © 2023 Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | ||||||
Access rights to Published version: | Restricted or Subscription Access | ||||||
Date of first compliant deposit: | 21 August 2023 | ||||||
Date of first compliant Open Access: | 22 August 2023 | ||||||
Conference Paper Type: | Paper | ||||||
Title of Event: | 26th IEEE International Conference on Intelligent Transportation Systems (ITSC 2023) | ||||||
Type of Event: | Conference | ||||||
Location of Event: | Bilbao, Bizkaia, Spain | ||||||
Date(s) of Event: | 24-28 Sep 2023 | ||||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year