Thomas Fel

According to our database, Thomas Fel authored at least 38 papers between 2020 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment.

Harrish Thasarathan, Julian Forsyth, Thomas Fel, Matthew Kowal, Konstantinos G. Derpanis

CoRR, February, 2025

Sparks of Explainability: Recent Advancements in Explaining Large Vision Models.

Thomas Fel

CoRR, February, 2025

An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures.

Thibaut Boissin, Franck Mamalet, Thomas Fel, Agustin Martin Picard, Thomas Massena, Mathieu Serrurier

CoRR, January, 2025

2024

Conformal prediction for trustworthy detection of railway signals.

Léo Andéol, Thomas Fel, Florence de Grancey, Luca Mossina

AI Ethics, February, 2024

Sparks of Explainability: Recent Advancements in Explaining Large Vision Models. (Lueurs d'Explicabilité : Avancées Récentes dans l'Explication des Grands Modèles de Vision).

Thomas Fel

PhD thesis, 2024

Local vs distributed representations: What is the right basis for interpretability?

Julien Colin, Lore Goetschalckx, Thomas Fel, Victor Boutin, Jay Gopal, Thomas Serre, Nuria Oliver

CoRR, 2024

Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models.

Mazda Moayeri, Vidhisha Balachandran, Varun Chandrasekaran, Safoora Yousefi, Thomas Fel, Soheil Feizi, Besmira Nushi, Neel Joshi, Vibhav Vineet

CoRR, 2024

One Wave to Explain Them All: A Unifying Perspective on Post-hoc Explainability.

Gabriel Kasmi, Amandine Brunetto, Thomas Fel, Jayneel Parekh

CoRR, 2024

Feature Accentuation: Revealing 'What' Features Respond to in Natural Images.

Chris J. Hamblin, Thomas Fel, Srijani Saha, Talia Konkle, George A. Alvarez

CoRR, 2024

Influenciæ: A Library for Tracing the Influence Back to the Data-Points.

Agustin Picard, Lucas Hervier, Thomas Fel, David Vigouroux

Proceedings of the Explainable Artificial Intelligence, 2024

Understanding Visual Feature Reliance through the Lens of Complexity.

Thomas Fel, Louis Béthune, Andrew K. Lampinen, Thomas Serre, Katherine L. Hermann

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks.

Victor Boutin, Rishav Mukherji, Aditya Agrawal, Sabine Muzellec, Thomas Fel, Thomas Serre, Rufin VanRullen

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Saliency strikes back: How filtering out high frequencies improves white-box explanations.

Sabine Muzellec, Thomas Fel, Victor Boutin, Léo Andéol, Rufin VanRullen, Thomas Serre

Proceedings of the Forty-first International Conference on Machine Learning, 2024

On the Foundations of Shortcut Learning.

Katherine L. Hermann, Hossein Mobahi, Thomas Fel, Michael Curtis Mozer

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Gradient strikes back: How filtering out high frequencies improves explanations.

Sabine Muzellec, Léo Andéol, Thomas Fel, Rufin VanRullen, Thomas Serre

CoRR, 2023

Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization.

Thomas Fel, Thibaut Boissin, Victor Boutin, Agustin Martin Picard, Paul Novello, Julien Colin, Drew Linsley, Tom Rousseau, Rémi Cadène, Laurent Gardes, Thomas Serre

CoRR, 2023

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

Drew Linsley, Ivan Felipe Rodríguez, Thomas Fel, Michael Arcaro, Saloni Sharma, Margaret S. Livingstone, Thomas Serre

CoRR, 2023

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

Drew Linsley, Pinyuan Feng, Thibaut Boissin, Alekh Karkada Ashok, Thomas Fel, Stephanie Olaiya, Thomas Serre

CoRR, 2023

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

Fanny Jourdan, Agustin Martin Picard, Thomas Fel, Laurent Risser, Jean-Michel Loubes, Nicholas Asher

CoRR, 2023

On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective.

Mathieu Serrurier, Franck Mamalet, Thomas Fel, Louis Béthune, Thibaut Boissin

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

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

Drew Linsley, Ivan F. Rodriguez Rodriguez, Thomas Fel, Michael Arcaro, Saloni Sharma, Margaret S. Livingstone, Thomas Serre

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization.

Thomas Fel, Thibaut Boissin, Victor Boutin, Agustin Picard, Paul Novello, Julien Colin, Drew Linsley, Tom Rousseau, Rémi Cadène, Lore Goetschalckx, Laurent Gardes, Thomas Serre

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

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

Thomas Fel, Victor Boutin, Louis Béthune, Rémi Cadène, Mazda Moayeri, Léo Andéol, Mathieu Chalvidal, Thomas Serre

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

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

Victor Boutin, Thomas Fel, Lakshya Singhal, Rishav Mukherji, Akash Nagaraj, Julien Colin, Thomas Serre

Proceedings of the International Conference on Machine Learning, 2023

CRAFT: Concept Recursive Activation FacTorization for Explainability.

Thomas Fel, Agustin Martin Picard, Louis Béthune, Thibaut Boissin, David Vigouroux, Julien Colin, Rémi Cadène, Thomas Serre

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

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

Thomas Fel, Melanie Ducoffe, David Vigouroux, Rémi Cadène, Mikael Capelle, Claire Nicodème, Thomas Serre

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

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

Léo Andéol, Thomas Fel, Florence de Grancey, Luca Mossina

Proceedings of the Conformal and Probabilistic Prediction with Applications, 2023

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

Fanny Jourdan, Agustin Martin Picard, Thomas Fel, Laurent Risser, Jean-Michel Loubes, Nicholas Asher

Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023, 2023

2022

Harmonizing the object recognition strategies of deep neural networks with humans.

Thomas Fel, Ivan Felipe Rodríguez, Drew Linsley, Thomas Serre

CoRR, 2022

Conviformers: Convolutionally guided Vision Transformer.

Mohit Vaishnav, Thomas Fel, Ivan Felipe Rodríguez, Thomas Serre

CoRR, 2022

When adversarial attacks become interpretable counterfactual explanations.

Mathieu Serrurier, Franck Mamalet, Thomas Fel, Louis Béthune, Thibaut Boissin

CoRR, 2022

Xplique: A Deep Learning Explainability Toolbox.

Thomas Fel, Lucas Hervier, David Vigouroux, Antonin Poché, Justin Plakoo, Rémi Cadène, Mathieu Chalvidal, Julien Colin, Thibaut Boissin, Louis Béthune, Agustin Martin Picard, Claire Nicodeme, Laurent Gardes, Grégory Flandin, Thomas Serre

CoRR, 2022

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

Thomas Fel, David Vigouroux, Rémi Cadène, Thomas Serre

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022

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

Paul Novello, Thomas Fel, David Vigouroux

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Harmonizing the object recognition strategies of deep neural networks with humans.

Thomas Fel, Ivan F. Rodriguez Rodriguez, Drew Linsley, Thomas Serre

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

Julien Colin, Thomas Fel, Rémi Cadène, Thomas Serre

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

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

Thomas Fel, Rémi Cadène, Mathieu Chalvidal, Matthieu Cord, David Vigouroux, Thomas Serre

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Representativity and Consistency Measures for Deep Neural Network Explanations.

Thomas Fel, David Vigouroux

CoRR, 2020