Autonomous driving has achieved significant milestones in research and development over
the last two decades. There is increasing interest in the field as the deployment of …

End-to-End driving is a promising paradigm as it circumvents the drawbacks associated with
modular systems, such as their overwhelming complexity and propensity for error …

Machine learning plays a role in many deployed decision systems, often in ways that are
difficult or impossible to understand by human stakeholders. Explaining, in a human …

This survey reviews explainability methods for vision-based self-driving systems trained with
behavior cloning. The concept of explainability has several facets and the need for …

Counterfactual explanations have shown promising results as a post-hoc framework to make
image classifiers more explainable. In this paper, we propose DiME, a method allowing the …

Nowadays, deep vision models are being widely deployed in safety-critical applications, eg,
autonomous driving, and explainability of such models is becoming a pressing concern …

Counterfactual explanations and adversarial attacks have a related goal: flip** output
labels with minimal perturbations regardless of their characteristics. Yet, adversarial attacks …

A visual counterfactual explanation replaces image regions in a query image with regions
from a distractor image such that the system's decision on the transformed image changes to …

In driving scenes, road agents often engage in frequent interaction and strive to understand
their surroundings. Ego-agent (each road agent itself) predicts what behavior will be …

Despite increasing progress in development of methods for generating visual counterfactual
explanations, previous works consider them as an entirely local technique. In this work, we …