Maxime Oquab

34 papers A* 7A 1Journal 21Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Efficient Universal Perception Encoder.
CoRR
Chenchen Zhu, Saksham Suri, Cijo Jose, Maxime Oquab, Marc Szafraniec, Wei Wen, Yunyang Xiong, Patrick Labatut, Piotr Bojanowski, Raghuraman Krishnamoorthi, Vikas Chandra
2025 J jnl
Cluster and Predict Latent Patches for Improved Masked Image Modeling.
CoRR
Timothée Darcet, Federico Baldassarre, Maxime Oquab, Julien Mairal, Piotr Bojanowski
2025 J jnl
Cluster and Predict Latents Patches for Improved Masked Image Modeling.
Trans. Mach. Learn. Res.
Timothée Darcet, Federico Baldassarre, Maxime Oquab, Julien Mairal, Piotr Bojanowski
2025 A* conf
DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment.
CVPR
Cijo Jose, Théo Moutakanni, Dahyun Kang, Federico Baldassarre, Timothée Darcet, Hu Xu, Daniel Li, Marc Szafraniec, Michaël Ramamonjisoa, Maxime Oquab, Oriane Siméoni, Huy V. Vo, Patrick Labatut, Piotr Bojanowski
2025 J jnl
DINOv3.
CoRR
Oriane Siméoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seung Eun Yi, Michaël Ramamonjisoa, Francisco Massa, Daniel Haziza, Luca Wehrstedt, Jianyuan Wang, Timothée Darcet, Théo Moutakanni, Leonel Sentana, Claire Roberts, Andrea Vedaldi, Jamie Tolan, John Brandt, Camille Couprie, Julien Mairal, Hervé Jégou, Patrick Labatut, Piotr Bojanowski
2024 J jnl
Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning.
CoRR
Théo Moutakanni, Piotr Bojanowski, Guillaume Chassagnon, Céline Hudelot, Armand Joulin, Yann LeCun, Matthew J. Muckley, Maxime Oquab, Marie-Pierre Revel, Maria Vakalopoulou
2024 J jnl
Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach.
CoRR
Huy V. Vo, Vasil Khalidov, Timothée Darcet, Théo Moutakanni, Nikita Smetanin, Marc Szafraniec, Hugo Touvron, Camille Couprie, Maxime Oquab, Armand Joulin, Hervé Jégou, Patrick Labatut, Piotr Bojanowski
2024 J jnl
Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach.
Trans. Mach. Learn. Res.
Huy V. Vo, Vasil Khalidov, Timothée Darcet, Théo Moutakanni, Nikita Smetanin, Marc Szafraniec, Hugo Touvron, Camille Couprie, Maxime Oquab, Armand Joulin, Hervé Jégou, Patrick Labatut, Piotr Bojanowski
2024 J jnl
DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment.
CoRR
Cijo Jose, Théo Moutakanni, Dahyun Kang, Federico Baldassarre, Timothée Darcet, Hu Xu, Daniel Li, Marc Szafraniec, Michaël Ramamonjisoa, Maxime Oquab, Oriane Siméoni, Huy V. Vo, Patrick Labatut, Piotr Bojanowski
2024 J jnl
DINOv2: Learning Robust Visual Features without Supervision.
Trans. Mach. Learn. Res.
Maxime Oquab, Timothée Darcet, Théo Moutakanni, Huy V. Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, Mido Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-wen Li, Ishan Misra, Michael Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Hervé Jégou, Julien Mairal, Patrick Labatut, Armand Joulin, Piotr Bojanowski
2024 A* conf
Vision Transformers Need Registers.
ICLR
Timothée Darcet, Maxime Oquab, Julien Mairal, Piotr Bojanowski
2024 J jnl
You Don't Need Data-Augmentation in Self-Supervised Learning.
CoRR
Théo Moutakanni, Maxime Oquab, Marc Szafraniec, Maria Vakalopoulou, Piotr Bojanowski
2024 A* conf
You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning.
NeurIPS
Théo Moutakanni, Maxime Oquab, Marc Szafraniec, Maria Vakalopoulou, Piotr Bojanowski
2023 A* conf
Co-training 2L Submodels for Visual Recognition.
CVPR
Hugo Touvron, Matthieu Cord, Maxime Oquab, Piotr Bojanowski, Jakob Verbeek, Hervé Jégou
2023 J jnl
DINOv2: Learning Robust Visual Features without Supervision.
CoRR
Maxime Oquab, Timothée Darcet, Théo Moutakanni, Huy V. Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, Mahmoud Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-wen Li, Ishan Misra, Michael G. Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Hervé Jégou, Julien Mairal, Patrick Labatut, Armand Joulin, Piotr Bojanowski
2023 J jnl
Vision Transformers Need Registers.
CoRR
Timothée Darcet, Maxime Oquab, Julien Mairal, Piotr Bojanowski
2022 J jnl
Co-training 2
CoRR
Hugo Touvron, Matthieu Cord, Maxime Oquab, Piotr Bojanowski, Jakob Verbeek, Hervé Jégou
2022 J jnl
Efficient conditioned face animation using frontally-viewed embedding.
CoRR
Maxime Oquab, Daniel Haziza, Ludovic Schwartz, Tao Xu, Katayoun Zand, Rui Wang, Peirong Liu, Camille Couprie
2021 J jnl
Can RNNs learn Recursive Nested Subject-Verb Agreements?
CoRR
Yair Lakretz, Theo Desbordes, Jean-Rémi King, Benoît Crabbé, Maxime Oquab, Stanislas Dehaene
2021 — conf
Low Bandwidth Video-Chat Compression Using Deep Generative Models.
CVPR Workshops
Maxime Oquab, Pierre Stock, Daniel Haziza, Tao Xu, Peizhao Zhang, Onur Celebi, Yana Hasson, Patrick Labatut, Bobo Bose-Kolanu, Thibault Peyronel, Camille Couprie
2021 J jnl
Self-appearance-aided Differential Evolution for Motion Transfer.
CoRR
Peirong Liu, Rui Wang, Xuefei Cao, Yipin Zhou, Ashish Shah, Maxime Oquab, Camille Couprie, Ser-Nam Lim
2020 J jnl
Back-to-back regression: Disentangling the influence of correlated factors from multivariate observations.
NeuroImage
Jean-Rémi King, François Charton, David Lopez-Paz, Maxime Oquab
2020 J jnl
Low Bandwidth Video-Chat Compression using Deep Generative Models.
CoRR
Maxime Oquab, Pierre Stock, Oran Gafni, Daniel Haziza, Tao Xu, Peizhao Zhang, Onur Celebi, Yana Hasson, Patrick Labatut, Bobo Bose-Kolanu, Thibault Peyronel, Camille Couprie
2019 A conf
Consistent population control: generate plenty of points, but with a bit of resampling.
FOGA
Vasil Khalidov, Maxime Oquab, Jérémy Rapin, Olivier Teytaud
2019 A* conf
Learning about an exponential amount of conditional distributions.
NeurIPS
Mohamed Ishmael Belghazi, Maxime Oquab, David Lopez-Paz
2019 J jnl
Learning about an exponential amount of conditional distributions.
CoRR
Mohamed Ishmael Belghazi, Maxime Oquab, Yann LeCun, David Lopez-Paz
2018 — —
Convolutional neural networks: towards less supervision for visual recognition. (Réseaux de neurones à convolution: vers moins de supervision pour la reconnaissance visuelle).
Maxime Oquab
2017 — conf
Geometrical Insights for Implicit Generative Modeling.
Braverman Readings in Machine Learning
Léon Bottou, Martín Arjovsky, David Lopez-Paz, Maxime Oquab
2017 J jnl
Geometrical Insights for Implicit Generative Modeling.
CoRR
Léon Bottou, Martín Arjovsky, David Lopez-Paz, Maxime Oquab
2017 — conf
Revisiting Classifier Two-Sample Tests.
ICLR (Poster)
David Lopez-Paz, Maxime Oquab
2016 — conf
ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization.
ECCV (5)
Vadim Kantorov, Maxime Oquab, Minsu Cho, Ivan Laptev
2016 J jnl
ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization.
CoRR
Vadim Kantorov, Maxime Oquab, Minsu Cho, Ivan Laptev
2015 A* conf
Is object localization for free? - Weakly-supervised learning with convolutional neural networks.
CVPR
Maxime Oquab, Léon Bottou, Ivan Laptev, Josef Sivic
2014 A* conf
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks.
CVPR
Maxime Oquab, Léon Bottou, Ivan Laptev, Josef Sivic