David Vigouroux

CRAFT: Concept Recursive Activation FacTorization for Explainability

Thomas Fel, Agustin Martin Picard, Louis Béthune et al. · 2023 · 69 citations · Full text

How Good is your Explanation? Algorithmic Stability Measures to Assess the Quality of Explanations for Deep Neural Networks

Thomas Fel, David Vigouroux, Rémi Cadène et al. · 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · 2022 · 21 citations · Full text

Artificial Intelligence, Relative Consistency Reco, Deep Neural Networks +13

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

Thomas Fel, Mélanie Ducoffe, David Vigouroux et al. · 2023 · 18 citations

Numerical Analysis, Convolutional Neural Network, Engineering +23

Look at the Variance! Efficient Black-box Explanations with Sobol-based\n Sensitivity Analysis

Thomas Fel, Rémi Cadène, Mathieu Chalvidal et al. · arXiv (Cornell University) · 2021 · 14 citations · Full text

Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis

Thomas Fel, Rémi Cadène, Mathieu Chalvidal et al. · HAL (Le Centre pour la Communication Scientifique Directe) · 2021 · 11 citations · Full text

Structured Prediction, Convolutional Neural Network, Engineering +27