11 citations · 28 across the 9 of their papers we have counts for
4 papers · 1 filter
CRAFT: Concept Recursive Activation FacTorization for Explainability
Thomas Fel, Agustin Picard, Louis Bethune +5
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 explaina…
Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure
Paul Novello, Thomas Fel, David Vigouroux
This paper presents a new efficient black-box attribution method based on Hilbert-Schmidt Independence Criterion (HSIC), a dependence measure based on Reproducing Kernel Hilbert Sp…
Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis
Thomas Fel, Melanie Ducoffe, David Vigouroux +4
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 i…
Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis
Thomas Fel, Remi Cadene, Mathieu Chalvidal +3
We describe a novel attribution method which is grounded in Sensitivity Analysis and uses Sobol indices. Beyond modeling the individual contributions of image regions, Sobol indice…