Thomas Fel | DeepAI

DeepAI AI Chat

Featured Co-authors

Matthieu Cord
95 publications
Jean-Michel Loubes
47 publications
Thomas Serre
39 publications
Rufin VanRullen
22 publications
Rémi Cadene
19 publications
Drew Linsley
14 publications
Louis Béthune
13 publications
Mathieu Serrurier
12 publications
Laurent Risser
11 publications
Nicholas Asher
11 publications
David Vigouroux
9 publications

∙ 07/18/2023

Gradient strikes back: How filtering out high frequencies improves explanations

Recent years have witnessed an explosion in the development of novel pre...

0 Sabine Muzellec, et al. ∙

∙ 06/11/2023

Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization

Feature visualization has gained substantial popularity, particularly af...

0 Thomas Fel, et al. ∙

∙ 06/11/2023

A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation

In recent years, concept-based approaches have emerged as some of the mo...

0 Thomas Fel, et al. ∙

∙ 06/06/2023

Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex

One of the most impactful findings in computational neuroscience over th...

0 Drew Linsley, et al. ∙

∙ 06/05/2023

Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception

Deep neural networks (DNNs) are known to have a fundamental sensitivity ...

0 Drew Linsley, et al. ∙

∙ 05/11/2023

COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks

Transformer architectures are complex and their use in NLP, while it has...

0 Fanny Jourdan, et al. ∙

∙ 04/12/2023

Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling

Deploying deep learning models in real-world certified systems requires ...

0 Léo Andéol, et al. ∙

∙ 01/27/2023

Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?

An important milestone for AI is the development of algorithms that can ...

0 Victor Boutin, et al. ∙

∙ 01/26/2023

Conformal Prediction for Trustworthy Detection of Railway Signals

We present an application of conformal prediction, a form of uncertainty...

0 Léo Andéol, et al. ∙

∙ 11/17/2022

CRAFT: Concept Recursive Activation FacTorization for Explainability

Attribution methods are a popular class of explainability methods that u...

0 Thomas Fel, et al. ∙

∙ 11/08/2022

Harmonizing the object recognition strategies of deep neural networks with humans

The many successes of deep neural networks (DNNs) over the past decade h...

0 Thomas Fel, et al. ∙

∙ 08/17/2022

Conviformers: Convolutionally guided Vision Transformer

Vision transformers are nowadays the de-facto preference for image class...

0 Mohit Vaishnav, et al. ∙

∙ 06/14/2022

When adversarial attacks become interpretable counterfactual explanations

We argue that, when learning a 1-Lipschitz neural network with the dual ...

0 Mathieu Serrurier, et al. ∙

∙ 06/13/2022

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

This paper presents a new efficient black-box attribution method based o...

0 Paul Novello, et al. ∙

∙ 06/09/2022

Xplique: A Deep Learning Explainability Toolbox

Today's most advanced machine-learning models are hardly scrutable. The ...

0 Thomas Fel, et al. ∙

∙ 02/15/2022

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

A variety of methods have been proposed to try to explain how deep neura...

17 Thomas Fel, et al. ∙

∙ 12/06/2021

What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods

A multitude of explainability methods and theoretical evaluation scores ...

0 Thomas Fel, et al. ∙

∙ 11/07/2021

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

We describe a novel attribution method which is grounded in Sensitivity ...

9 Thomas Fel, et al. ∙

∙ 09/07/2020

Representativity and Consistency Measures for Deep Neural Network Explanations

The adoption of machine learning in critical contexts requires a reliabl...

0 Thomas Fel, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world