| What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods T Fel, J Colin, R Cadène, T Serre NeurIPS 2022, Advances in Neural Information Processing Systems, 2021 | 74 | 2021 |
| Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis T Fel, R Cadene, M Chalvidal, M Cord, D Vigouroux, T Serre NeurIPS 2021, Advances in Neural Information Processing Systems, 2021 | 64 | 2021 |
| Craft: Concept recursive activation factorization for explainability T Fel, A Picard, L Bethune, T Boissin, D Vigouroux, J Colin, R Cadène, ... CVPR 2023, Proceedings of the IEEE/CVF Conference on Computer Vision and …, 2023 | 62 | 2023 |
| How good is your explanation? algorithmic stability measures to assess the quality of explanations for deep neural networks T Fel, D Vigouroux, R Cadène, T Serre WACV 2022, Proceedings of the IEEE/CVF Winter Conference on Applications of …, 2022 | 59* | 2022 |
| Harmonizing the object recognition strategies of deep neural networks with humans T Fel, I Felipe, D Linsley, T Serre NeurIPS 2022, Advances in Neural Information Processing Systems, 2022 | 54 | 2022 |
| Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis T Fel, M Ducoffe, D Vigouroux, R Cadène, M Capelle, C Nicodème, ... CVPR 2023, Proceedings of the IEEE/CVF Conference on Computer Vision and …, 2022 | 31 | 2022 |
| Xplique: A Deep Learning Explainability Toolbox T Fel, L Hervier, D Vigouroux, A Poche, J Plakoo, R Cadene, M Chalvidal, ... CVPR 2022, Workshop on Explainable Artificial Intelligence for Computer …, 2022 | 26 | 2022 |
| Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure P Novello, T Fel, D Vigouroux NeurIPS 2022, Advances in Neural Information Processing Systems, 2022 | 21 | 2022 |
| A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation T Fel, V Boutin, M Moayeri, R Cadène, L Bethune, M Chalvidal, T Serre NeurIPS 2023, Advances in Neural Information Processing Systems, 2023 | 16 | 2023 |
| On the Foundations of Shortcut Learning KL Hermann, H Mobahi, T Fel, MC Mozer ICLR 2024, International Conference on Learning Representations, 2023 | 13 | 2023 |
| On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective M Serrurier, F Mamalet, T Fel, L Béthune, T Boissin NeurIPS 2023, Advances in Neural Information Processing Systems, 2023 | 10* | 2023 |
| Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization T Fel, T Boissin, V Boutin, A Picard, P Novello, J Colin, D Linsley, ... NeurIPS 2023, Advances in Neural Information Processing Systems, 2023 | 10 | 2023 |
| Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex D Linsley, IF Rodriguez, T Fel, M Arcaro, S Sharma, M Livingstone, ... NeurIPS 2023, Advances in Neural Information Processing Systems, 2023 | 8 | 2023 |
| Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines? V Boutin, T Fel, L Singhal, R Mukherji, A Nagaraj, J Colin, T Serre ICML 2023, Proceedings of the International Conference on Machine Learning, 2023 | 8 | 2023 |
| Can we reconcile safety objectives with machine learning performances? L Alecu, H Bonnin, T Fel, L Gardes, S Gerchinovitz, L Ponsolle, F Mamalet, ... ERTS 2022, 2022 | 8 | 2022 |
| COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks F Jourdan, A Picard, T Fel, L Risser, JM Loubes, N Asher ACL 2023, Proceedings of the Annual Meeting of the Association for …, 2023 | 7 | 2023 |
| Conviformers: Convolutionally guided vision transformer M Vaishnav, T Fel, IF Rodríguez, T Serre arXiv preprint arXiv:2208.08900, 2022 | 3 | 2022 |
| Influenciæ: A library for tracing the influence back to the data-points A Picard, L Hervier, T Fel, D Vigouroux World Conference on Explainable Artificial Intelligence, 193-204, 2024 | 2 | 2024 |
| Conformal prediction for trustworthy detection of railway signals L Andéol, T Fel, F de Grancey, L Mossina AI and Ethics 4 (1), 157-161, 2024 | 2 | 2024 |
| Feature Accentuation: Revealing'What'Features Respond to in Natural Images C Hamblin, T Fel, S Saha, T Konkle, G Alvarez arXiv preprint arXiv:2402.10039, 2024 | 1 | 2024 |
Thomas SerreProfessor, Brown University and ANR-3IA Artificial and Natural Intelligence Toulouse InstituteVerified email at brown.edu
