The rapid development of Artificial Intelligence (AI) has revolutionized numerous fields, with
large language models (LLMs) and computer vision (CV) systems driving advancements in …

Ensuring both transparency and safety is critical when deploying Deep Neural Networks
(DNNs) in high-risk applications such as medicine. The field of explainable AI (XAI) has …

Abstract Concept Bottleneck Models (CBMs) have recently been proposed to address the
'black-box'problem of deep neural networks, by first mapping images to a human …

Deep-learning models can extract a rich assortment of features from data. Which features a
model uses depends not only on predictivity-how reliably a feature indicates train-set labels …

This paper studies the problem of concept-based interpretability of transformer
representations for videos. Concretely we seek to explain the decision-making process of …

Concept-based XAI (C-XAI) approaches to explaining neural vision models are a promising
field of research, since explanations that refer to concepts (ie, semantically meaningful parts …

CLIP embeddings have demonstrated remarkable performance across a wide range of
computer vision tasks. However, these high-dimensional, dense vector representations are …

Research on Explainable Artificial Intelligence has recently started exploring the idea of
producing explanations that, rather than being expressed in terms of low-level features, are …

Abstract Deep Neural Networks are prone to learning and relying on spurious correlations in
the training data which for high-risk applications can have fatal consequences. Various …

Vision transformers (ViTs) can be trained using various learning paradigms, from fully
supervised to self-supervised. Diverse training protocols often result in significantly different …