Следене
Olivier J Hénaff
Olivier J Hénaff
Google DeepMind
Потвърден имейл адрес: google.com - Начална страница
Заглавие
Позовавания
Позовавания
Година
Data-efficient image recognition with contrastive predictive coding
OJ Hénaff, A Srinivas, J De Fauw, A Razavi, C Doersch, SMA Eslami, ...
International Conference on Machine Learning, 4182-4192, 2020
16322020
Perceiver io: A general architecture for structured inputs & outputs
A Jaegle, S Borgeaud, JB Alayrac, C Doersch, C Ionescu, D Ding, ...
arXiv preprint arXiv:2107.14795, 2021
5912021
Are we done with imagenet?
L Beyer, OJ Hénaff, A Kolesnikov, X Zhai, A Oord
arXiv preprint arXiv:2006.07159, 2020
4222020
Efficient visual pretraining with contrastive detection
OJ Hénaff, S Koppula, JB Alayrac, A Van den Oord, O Vinyals, J Carreira
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
1802021
Divide and contrast: Self-supervised learning from uncurated data
Y Tian, OJ Henaff, A Van den Oord
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
1012021
Object discovery and representation networks
OJ Hénaff, S Koppula, E Shelhamer, D Zoran, A Jaegle, A Zisserman, ...
European conference on computer vision, 123-143, 2022
962022
Perceptual straightening of natural videos
OJ Hénaff, RLT Goris, EP Simoncelli
Nature neuroscience 22 (6), 984-991, 2019
962019
Paligemma: A versatile 3b vlm for transfer
L Beyer, A Steiner, AS Pinto, A Kolesnikov, X Wang, D Salz, M Neumann, ...
arXiv preprint arXiv:2407.07726, 2024
602024
Geodesics of learned representations
OJ Hénaff, EP Simoncelli
International Conference on Learning Representations (ICLR) 2016, 2015
582015
Representation of visual uncertainty through neural gain variability
OJ Hénaff, ZM Boundy-Singer, K Meding, CM Ziemba, RLT Goris
Nature communications 11 (1), 2513, 2020
512020
Primary visual cortex straightens natural video trajectories
OJ Hénaff, Y Bai, JA Charlton, I Nauhaus, EP Simoncelli, RLT Goris
Nature communications 12 (1), 5982, 2021
452021
Towards in-context scene understanding
I Balazevic, D Steiner, N Parthasarathy, R Arandjelović, O Henaff
Advances in Neural Information Processing Systems 36, 2024
282024
Self-supervised video pretraining yields robust and more human-aligned visual representations
N Parthasarathy, SM Eslami, J Carreira, O Henaff
Advances in Neural Information Processing Systems 36, 65743-65765, 2023
28*2023
The local low-dimensionality of natural images
OJ Hénaff, J Ballé, NC Rabinowitz, EP Simoncelli
International Conference on Learning Representations (ICLR) 2015, 2014
172014
Memory consolidation enables long-context video understanding
I Balazevic, Y Shi, P Papalampidi, R Chaabouni, S Koppula, OJ Hénaff
Forty-first International Conference on Machine Learning, 2024
13*2024
Three ways to improve feature alignment for open vocabulary detection
R Arandjelović, A Andonian, A Mensch, OJ Hénaff, JB Alayrac, ...
arXiv preprint arXiv:2303.13518, 2023
122023
Where should i spend my flops? efficiency evaluations of visual pre-training methods
S Koppula, Y Li, E Shelhamer, A Jaegle, N Parthasarathy, R Arandjelovic, ...
arXiv preprint arXiv:2209.15589, 2022
112022
Bad students make great teachers: Active learning accelerates large-scale visual understanding
T Evans, S Pathak, H Merzic, J Schwarz, R Tanno, OJ Henaff
arXiv preprint arXiv:2312.05328, 2023
82023
Fantastic gains and where to find them: On the existence and prospect of general knowledge transfer between any pretrained model
K Roth, L Thede, AS Koepke, O Vinyals, O Hénaff, Z Akata
arXiv preprint arXiv:2310.17653, 2023
72023
Data curation via joint example selection further accelerates multimodal learning
T Evans, N Parthasarathy, H Merzic, OJ Henaff
arXiv preprint arXiv:2406.17711, 2024
52024
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20