Text-conditioned image editing has recently attracted considerable interest. However, most
methods are currently limited to one of the following: specific editing types (eg, object …

The field of explainable artificial intelligence (XAI) aims to bring transparency to today's
powerful but opaque deep learning models. While local XAI methods explain individual …

Concept Bottleneck Models (CBMs) map the inputs onto a set of interpretable concepts
(``the bottleneck'') and use the concepts to make predictions. A concept bottleneck enhances …

GAN inversion aims to invert a given image back into the latent space of a pretrained GAN
model so that the image can be faithfully reconstructed from the inverted code by the …

Deep neural networks often rely on spurious correlations to make predictions, which hinders
generalization beyond training environments. For instance, models that associate cats with …

The rise of sophisticated black-box machine learning models in Artificial Intelligence
systems has prompted the need for explanation methods that reveal how these models work …

While hypothesis testing is a highly formalized activity, hypothesis generation remains
largely informal. We propose a systematic procedure to generate novel hypotheses about …

Abstract Visual Counterfactual Explanations (VCEs) are an important tool to understand the
decisions of an image classifier. They are “small” but “realistic” semantic changes of the …

Abstract Machine learning models have been found to learn shortcuts---unintended decision
rules that are unable to generalize---undermining models' reliability. Previous works address …

Explainable Artificial Intelligence (XAI) has emerged as a crucial research area to address
the interpretability challenges posed by complex machine learning models. In this survey …