SAFE: Saliency-Aware Counterfactual Explanations for DNN-based Automated Driving Systems
This work addresses the need for better interpretability in safety-critical automated driving systems, though it appears incremental as it builds on existing counterfactual methods with a focus on saliency.
The paper tackles the problem of generating counterfactual explanations for deep neural networks in automated driving systems by addressing that current methods may not produce examples near the decision boundary, and it proposes a saliency-aware approach to create more informative explanations.
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. Source codes are available at: https://github.com/Amir-Samadi//Saliency_Aware_CF.