Thomas Fel

Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis

2022 · arXiv (Cornell University)

A variety of methods have been proposed to try to explain how deep neural networks make their decisions. Key to those approaches is the need to sample the pixel space efficiently in order to derive …

CRAFT: Concept Recursive Activation FacTorization for Explainability

2022 · arXiv (Cornell University)

Attribution methods, which employ heatmaps to identify the most influential regions of an image that impact model decisions, have gained widespread popularity as a type of explainability method. However, recent research has exposed the limited …

Understanding Visual Feature Reliance through the Lens of Complexity

2024 · arXiv (Cornell University)

Recent studies suggest that deep learning models inductive bias towards favoring simpler features may be one of the sources of shortcut learning. Yet, there has been limited focus on understanding the complexity of the myriad …

Back to the Baseline: Examining Baseline Effects on Explainability Metrics

2025 · arXiv (Cornell University)

Attribution methods are among the most prevalent techniques in Explainable Artificial Intelligence (XAI) and are usually evaluated and compared using Fidelity metrics, with Insertion and Deletion being the most popular. These metrics rely on a …