Thomas Fel

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 38

Top Topics

Object Detection

Diffusion Models

Top Venues

Publications

Chris J. Hamblin, Thomas Fel, Srijani Saha, Talia Konkle, George A. Alvarez
Feature Accentuation: Revealing 'What' Features Respond to in Natural Images. CoRR (2024)
Katherine L. Hermann, Hossein Mobahi, Thomas Fel, Michael Curtis Mozer
On the Foundations of Shortcut Learning. ICLR (2024)
Thomas Fel, Louis Béthune, Andrew Kyle Lampinen, Thomas Serre, Katherine L. Hermann
Understanding Visual Feature Reliance through the Lens of Complexity. CoRR (2024)
Victor Boutin, Rishav Mukherji, Aditya Agrawal, Sabine Muzellec, Thomas Fel, Thomas Serre, Rufin VanRullen
Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks. CoRR (2024)
Léo Andéol, Thomas Fel, Florence de Grancey, Luca Mossina
Conformal prediction for trustworthy detection of railway signals. AI Ethics 4 (1) (2024)
Drew Linsley, Ivan Felipe Rodríguez, Thomas Fel, Michael Arcaro, Saloni Sharma, Margaret S. Livingstone, Thomas Serre
Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex. CoRR (2023)
Léo Andéol, Thomas Fel, Florence De Grancey, Luca Mossina
Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling. COPA (2023)
Thomas Fel, Agustin Picard, Louis Béthune, Thibaut Boissin, David Vigouroux, Julien Colin, Rémi Cadènc, Thomas Serre
CRAFT: Concept Recursive Activation FacTorization for Explainability. CVPR (2023)
Katherine L. Hermann, Hossein Mobahi, Thomas Fel, Michael C. Mozer
On the Foundations of Shortcut Learning. CoRR (2023)
Drew Linsley, Ivan F. Rodriguez Rodriguez, Thomas Fel, Michael Arcaro, Saloni Sharma, Margaret S. Livingstone, Thomas Serre
Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex. NeurIPS (2023)
Thomas Fel, Thibaut Boissin, Victor Boutin, Agustin Picard, Paul Novello, Julien Colin, Drew Linsley, Tom Rousseau, Rémi Cadène, Lore Goetschalckx, Laurent Gardes, Thomas Serre
Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization. NeurIPS (2023)
Fanny Jourdan, Agustin Picard, Thomas Fel, Laurent Risser, Jean-Michel Loubes, Nicholas Asher
COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP. ACL (Findings) (2023)
Thomas Fel, Thibaut Boissin, Victor Boutin, Agustin Picard, Paul Novello, Julien Colin, Drew Linsley, Tom Rousseau, Rémi Cadène, Laurent Gardes, Thomas Serre
Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization. CoRR (2023)
Victor Boutin, Thomas Fel, Lakshya Singhal, Rishav Mukherji, Akash Nagaraj, Julien Colin, Thomas Serre
Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines? ICML (2023)
Victor Boutin, Thomas Fel, Lakshya Singhal, Rishav Mukherji, Akash Nagaraj, Julien Colin, Thomas Serre
Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines? CoRR (2023)
Fanny Jourdan, Agustin Picard, Thomas Fel, Laurent Risser, Jean-Michel Loubes, Nicholas Asher
COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks. CoRR (2023)
Mathieu Serrurier, Franck Mamalet, Thomas Fel, Louis Béthune, Thibaut Boissin
On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective. NeurIPS (2023)
Thomas Fel, Victor Boutin, Louis Béthune, Rémi Cadène, Mazda Moayeri, Léo Andéol, Mathieu Chalvidal, Thomas Serre
A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation. NeurIPS (2023)
Drew Linsley, Pinyuan Feng, Thibaut Boissin, Alekh Karkada Ashok, Thomas Fel, Stephanie Olaiya, Thomas Serre
Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception. CoRR (2023)
Léo Andéol, Thomas Fel, Florence De Grancey, Luca Mossina
Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling. CoRR (2023)
Sabine Muzellec, Léo Andéol, Thomas Fel, Rufin VanRullen, Thomas Serre
Gradient strikes back: How filtering out high frequencies improves explanations. CoRR (2023)
Thomas Fel, Melanie Ducoffe, David Vigouroux, Rémi Cadène, Mikael Capelle, Claire Nicodème, Thomas Serre
Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis. CVPR (2023)
Thomas Fel, Victor Boutin, Mazda Moayeri, Rémi Cadène, Louis Béthune, Léo Andéol, Mathieu Chalvidal, Thomas Serre
A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation. CoRR (2023)
Paul Novello, Thomas Fel, David Vigouroux
Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure. CoRR (2022)
Thomas Fel, Ivan Felipe Rodríguez, Drew Linsley, Thomas Serre
Harmonizing the object recognition strategies of deep neural networks with humans. CoRR (2022)
Thomas Fel, Melanie Ducoffe, David Vigouroux, Rémi Cadène, Mikael Capelle, Claire Nicodeme, Thomas Serre
Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis. CoRR (2022)
Paul Novello, Thomas Fel, David Vigouroux
Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure. NeurIPS (2022)
Thomas Fel, Lucas Hervier, David Vigouroux, Antonin Poche, Justin Plakoo, Rémi Cadène, Mathieu Chalvidal, Julien Colin, Thibaut Boissin, Louis Béthune, Agustin Picard, Claire Nicodeme, Laurent Gardes, Grégory Flandin, Thomas Serre
Xplique: A Deep Learning Explainability Toolbox. CoRR (2022)
Thomas Fel, Ivan F. Rodriguez Rodriguez, Drew Linsley, Thomas Serre
Harmonizing the object recognition strategies of deep neural networks with humans. NeurIPS (2022)
Julien Colin, Thomas Fel, Rémi Cadène, Thomas Serre
What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods. NeurIPS (2022)
Mathieu Serrurier, Franck Mamalet, Thomas Fel, Louis Béthune, Thibaut Boissin
When adversarial attacks become interpretable counterfactual explanations. CoRR (2022)
Thomas Fel, David Vigouroux, Rémi Cadène, Thomas Serre
How Good is your Explanation? Algorithmic Stability Measures to Assess the Quality of Explanations for Deep Neural Networks. WACV (2022)
Thomas Fel, Agustin Picard, Louis Béthune, Thibaut Boissin, David Vigouroux, Julien Colin, Rémi Cadène, Thomas Serre
CRAFT: Concept Recursive Activation FacTorization for Explainability. CoRR (2022)
Mohit Vaishnav, Thomas Fel, Ivan Felipe Rodríguez, Thomas Serre
Conviformers: Convolutionally guided Vision Transformer. CoRR (2022)
Thomas Fel, Rémi Cadène, Mathieu Chalvidal, Matthieu Cord, David Vigouroux, Thomas Serre
Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis. NeurIPS (2021)
Thomas Fel, Julien Colin, Rémi Cadène, Thomas Serre
What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods. CoRR (2021)
Thomas Fel, Rémi Cadène, Mathieu Chalvidal, Matthieu Cord, David Vigouroux, Thomas Serre
Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis. CoRR (2021)
Thomas Fel, David Vigouroux
Representativity and Consistency Measures for Deep Neural Network Explanations. CoRR (2020)