Author

David Vigouroux

Observed name: Vigouroux, David

Observed institutions: Office National d'Études et de Recherches Aérospatiales, IMT Atlantique, IRT Saint Exupéry, Université de Toulouse

OpenAlex ID: A5086261580

CRAFT: Concept Recursive Activation FacTorization for Explainability

2023 · Thomas Fel, Agustin Picard, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 120

PDF

Xplique: A Deep Learning Explainability Toolbox

2022 · Fel, Thomas, Hervier, Lucas, et al. · arXiv (Cornell University) · 42

PDF

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

2021 · Fel, Thomas, Cadene, Remi, et al. · arXiv (Cornell University) · 39

PDF

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

2022 · Thomas Fel, David Vigouroux, et al. · IEEE Winter Conference on Applications of Computer Vision · 37

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

2023 · Thomas Fel, Melanie Ducoffe, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 35

PDF

Making Sense of Dependence: Efficient Black-Box Explanations Using Dependence Measure

2022 · Paul Novello, Thomas Fel, et al. · neural information processing systems · 21

Object Detection with Probabilistic Guarantees: A Conformal Prediction Approach

2022 · Florence de Grancey, Jean-Luc Adam, et al. · Lecture notes in computer science · 12

Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure

2022 · Novello, Paul, Fel, Thomas, et al. · arXiv (Cornell University) · 11

PDF

Representativity and Consistency Measures for Deep Neural Network Explanations

2020 · Thomas Fel, David Vigouroux · arXiv (Cornell University) · 9

PDF

How to design a dataset compliant with an ML-based system ODD?