Diane Bouchacourt

Publication Activity (10 Years)

Years Active: 2015-2024
Publications (10 Years): 49

Top Topics

Object Recognition

Visual Representations

Top Venues

Publications

Mazda Moayeri, Michael Rabbat, Mark Ibrahim, Diane Bouchacourt
Embracing Diversity: Interpretable Zero-shot Classification Beyond One Vector Per Class. FAccT (2024)
Megan Richards, Polina Kirichenko, Diane Bouchacourt, Mark Ibrahim
Does Progress On Object Recognition Benchmarks Improve Generalization on Crowdsourced, Global Data? ICLR (2024)
Vlad Sobal, Mark Ibrahim, Randall Balestriero, Vivien Cabannes, Diane Bouchacourt, Pietro Astolfi, Kyunghyun Cho, Yann LeCun
𝕏-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs. CoRR (2024)
Florian Bordes, Richard Yuanzhe Pang, Anurag Ajay, Alexander C. Li, Adrien Bardes, Suzanne Petryk, Oscar Mañas, Zhiqiu Lin, Anas Mahmoud, Bargav Jayaraman, Mark Ibrahim, Melissa Hall, Yunyang Xiong, Jonathan Lebensold, Candace Ross, Srihari Jayakumar, Chuan Guo, Diane Bouchacourt, Haider Al-Tahan, Karthik Padthe, Vasu Sharma, Hu Xu, Xiaoqing Ellen Tan, Megan Richards, Samuel Lavoie, Pietro Astolfi, Reyhane Askari Hemmat, Jun Chen, Kushal Tirumala, Rim Assouel, Mazda Moayeri, Arjang Talattof, Kamalika Chaudhuri, Zechun Liu, Xilun Chen, Quentin Garrido, Karen Ullrich, Aishwarya Agrawal, Kate Saenko, Asli Celikyilmaz, Vikas Chandra
An Introduction to Vision-Language Modeling. CoRR (2024)
Polina Kirichenko, Mark Ibrahim, Randall Balestriero, Diane Bouchacourt, Ramakrishna Vedantam, Hamed Firooz, Andrew Gordon Wilson
Understanding the Detrimental Class-level Effects of Data Augmentation. CoRR (2024)
Ouail Kitouni, Niklas Nolte, Diane Bouchacourt, Adina Williams, Mike Rabbat, Mark Ibrahim
The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More. CoRR (2024)
Mazda Moayeri, Michael Rabbat, Mark Ibrahim, Diane Bouchacourt
Embracing Diversity: Interpretable Zero-shot classification beyond one vector per class. CoRR (2024)
Florian Bordes, Shashank Shekhar, Mark Ibrahim, Diane Bouchacourt, Pascal Vincent, Ari S. Morcos
PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning. CoRR (2023)
Alberto Bietti, Vivien Cabannes, Diane Bouchacourt, Hervé Jégou, Léon Bottou
Birth of a Transformer: A Memory Viewpoint. NeurIPS (2023)
Polina Kirichenko, Mark Ibrahim, Randall Balestriero, Diane Bouchacourt, Shanmukha Ramakrishna Vedantam, Hamed Firooz, Andrew Gordon Wilson
Understanding the detrimental class-level effects of data augmentation. NeurIPS (2023)
Badr Youbi Idrissi, Diane Bouchacourt, Randall Balestriero, Ivan Evtimov, Caner Hazirbas, Nicolas Ballas, Pascal Vincent, Michal Drozdzal, David Lopez-Paz, Mark Ibrahim
ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations. ICLR (2023)
Megan Richards, Polina Kirichenko, Diane Bouchacourt, Mark Ibrahim
Does Progress On Object Recognition Benchmarks Improve Real-World Generalization? CoRR (2023)
Florian Bordes, Shashank Shekhar, Mark Ibrahim, Diane Bouchacourt, Pascal Vincent, Ari Morcos
PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning. NeurIPS (2023)
Karsten Roth, Mark Ibrahim, Zeynep Akata, Pascal Vincent, Diane Bouchacourt
Disentanglement of Correlated Factors via Hausdorff Factorized Support. ICLR (2023)
Alberto Bietti, Vivien Cabannes, Diane Bouchacourt, Hervé Jégou, Léon Bottou
Birth of a Transformer: A Memory Viewpoint. CoRR (2023)
Mark Ibrahim, Quentin Garrido, Ari S. Morcos, Diane Bouchacourt
The Robustness Limits of SoTA Vision Models to Natural Variation. Trans. Mach. Learn. Res. 2023 (2023)
Laura Gustafson, Megan Richards, Melissa Hall, Caner Hazirbas, Diane Bouchacourt, Mark Ibrahim
Exploring Why Object Recognition Performance Degrades Across Income Levels and Geographies with Factor Annotations. NeurIPS (2023)
Laura Gustafson, Megan Richards, Melissa Hall, Caner Hazirbas, Diane Bouchacourt, Mark Ibrahim
Pinpointing Why Object Recognition Performance Degrades Across Income Levels and Geographies. CoRR (2023)
Mohammad Pezeshki, Diane Bouchacourt, Mark Ibrahim, Nicolas Ballas, Pascal Vincent, David Lopez-Paz
Discovering environments with XRM. CoRR (2023)
Cian Eastwood, Julius von Kügelgen, Linus Ericsson, Diane Bouchacourt, Pascal Vincent, Bernhard Schölkopf, Mark Ibrahim
Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations. CoRR (2023)
Karsten Roth, Mark Ibrahim, Zeynep Akata, Pascal Vincent, Diane Bouchacourt
Disentanglement of Correlated Factors via Hausdorff Factorized Support. CoRR (2022)
Mark Ibrahim, Quentin Garrido, Ari Morcos, Diane Bouchacourt
The Robustness Limits of SoTA Vision Models to Natural Variation. CoRR (2022)
David Lopez-Paz, Diane Bouchacourt, Levent Sagun, Nicolas Usunier
Measuring and signing fairness as performance under multiple stakeholder distributions. CoRR (2022)
Badr Youbi Idrissi, Diane Bouchacourt, Randall Balestriero, Ivan Evtimov, Caner Hazirbas, Nicolas Ballas, Pascal Vincent, Michal Drozdzal, David Lopez-Paz, Mark Ibrahim
ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations. CoRR (2022)
Mark Ibrahim, Diane Bouchacourt, Ari S. Morcos
Robust Self-Supervised Learning with Lie Groups. CoRR (2022)
Diane Bouchacourt, Mark Ibrahim, Stéphane Deny
Addressing the Topological Defects of Disentanglement via Distributed Operators. CoRR (2021)
Diane Bouchacourt, Mark Ibrahim, Ari S. Morcos
Grounding inductive biases in natural images: invariance stems from variations in data. CoRR (2021)
Diane Bouchacourt, Mark Ibrahim, Ari S. Morcos
Grounding inductive biases in natural images: invariance stems from variations in data. NeurIPS (2021)
Laura Ruis, Jacob Andreas, Marco Baroni, Diane Bouchacourt, Brenden M. Lake
A Benchmark for Systematic Generalization in Grounded Language Understanding. CoRR (2020)
Rahma Chaabouni, Eugene Kharitonov, Diane Bouchacourt, Emmanuel Dupoux, Marco Baroni
Compositionality and Generalization In Emergent Languages. ACL (2020)
Jonathan Gordon, David Lopez-Paz, Marco Baroni, Diane Bouchacourt
Permutation Equivariant Models for Compositional Generalization in Language. ICLR (2020)
Laura Ruis, Jacob Andreas, Marco Baroni, Diane Bouchacourt, Brenden M. Lake
A Benchmark for Systematic Generalization in Grounded Language Understanding. NeurIPS (2020)
Rahma Chaabouni, Eugene Kharitonov, Diane Bouchacourt, Emmanuel Dupoux, Marco Baroni
Compositionality and Generalization in Emergent Languages. CoRR (2020)
Christina Heinze-Deml, Diane Bouchacourt
Think before you act: A simple baseline for compositional generalization. CoRR (2020)
Eugene Kharitonov, Rahma Chaabouni, Diane Bouchacourt, Marco Baroni
Entropy Minimization In Emergent Languages. ICML (2020)
Diane Bouchacourt, Marco Baroni
Miss Tools and Mr Fruit: Emergent Communication in Agents Learning about Object Affordances. ACL (1) (2019)
Eugene Kharitonov, Rahma Chaabouni, Diane Bouchacourt, Marco Baroni
EGG: a toolkit for research on Emergence of lanGuage in Games. EMNLP/IJCNLP (3) (2019)
Eugene Kharitonov, Rahma Chaabouni, Diane Bouchacourt, Marco Baroni
EGG: a toolkit for research on Emergence of lanGuage in Games. CoRR (2019)
Roberto Dessì, Diane Bouchacourt, Davide Crepaldi, Marco Baroni
Focus on What's Informative and Ignore What's not: Communication Strategies in a Referential Game. CoRR (2019)
Diane Bouchacourt, Ludovic Denoyer
EDUCE: Explaining model Decisions through Unsupervised Concepts Extraction. CoRR (2019)
Eugene Kharitonov, Rahma Chaabouni, Diane Bouchacourt, Marco Baroni
Information Minimization In Emergent Languages. CoRR (2019)
Mathijs Mul, Diane Bouchacourt, Elia Bruni
Mastering emergent language: learning to guide in simulated navigation. CoRR (2019)
Diane Bouchacourt, Marco Baroni
Miss Tools and Mr Fruit: Emergent communication in agents learning about object affordances. CoRR (2019)
Diane Bouchacourt, Marco Baroni
How agents see things: On visual representations in an emergent language game. EMNLP (2018)
Diane Bouchacourt, Ryota Tomioka, Sebastian Nowozin
Multi-Level Variational Autoencoder: Learning Disentangled Representations From Grouped Observations. AAAI (2018)
Diane Bouchacourt, Marco Baroni
How agents see things: On visual representations in an emergent language game. CoRR (2018)
Diane Bouchacourt, Ryota Tomioka, Sebastian Nowozin
Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations. CoRR (2017)
Diane Bouchacourt, M. Pawan Kumar, Sebastian Nowozin
DISCO Nets: DISsimilarity COefficient Networks. CoRR (2016)
Diane Bouchacourt, Pawan Kumar Mudigonda, Sebastian Nowozin
DISCO Nets : DISsimilarity COefficients Networks. NIPS (2016)
Diane Bouchacourt, Sebastian Nowozin, M. Pawan Kumar
Entropy-Based Latent Structured Output Prediction. ICCV (2015)