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 …

Despite the proliferation of explainable AI (XAI) methods, little is understood about end-
users' explainability needs and behaviors around XAI explanations. To address this gap and …

As AI technology is increasingly applied to high-impact, high-risk domains, there have been
a number of new methods aimed at making AI models more human interpretable. Despite …

Multimodal pre-trained models, such as CLIP, are popular for zero-shot classification due to
their open-vocabulary flexibility and high performance. However, vision-language models …

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 …

As machine learning (ML) models and datasets increase in complexity, the demand for
methods that enhance explainability and interpretability becomes paramount. Prototypes, by …

Enhancing model performance in agricultural image analysis faces challenges due to
limited datasets, biological variability, and uncontrolled environments. Deep learning …

Counterfactual explanations have been argued to be one of the most intuitive forms of
explanation. They are typically defined as a minimal set of edits on a given data sample that …