Daniel Haziza
Daniel Haziza
Facebook AI Research (FAIR)
Verified email at
Cited by
Cited by
Dinov2: Learning robust visual features without supervision
M Oquab, T Darcet, T Moutakanni, H Vo, M Szafraniec, V Khalidov, ...
arXiv preprint arXiv:2304.07193, 2023
VoxPopuli: A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation
C Wang, M Riviere, A Lee, A Wu, C Talnikar, D Haziza, M Williamson, ...
arXiv preprint arXiv:2101.00390, 2021
Expert level control of ramp metering based on multi-task deep reinforcement learning
F Belletti, D Haziza, G Gomes, AM Bayen
IEEE Transactions on Intelligent Transportation Systems 19 (4), 1198-1207, 2017
xFormers: A modular and hackable transformer modelling library
B Lefaudeux, F Massa, D Liskovich, W Xiong, V Caggiano, S Naren, M Xu, ...
Low bandwidth video-chat compression using deep generative models
M Oquab, P Stock, D Haziza, T Xu, P Zhang, O Celebi, Y Hasson, ...
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2021
Hiplot, interactive high-dimensionality plots
D Haziza, J Rapin, G Synnaeve
Github repository, 2020
Open source evolutionary structured optimization
J Rapin, P Bennet, E Centeno, D Haziza, A Moreau, O Teytaud
Proceedings of the 2020 Genetic and Evolutionary Computation Conference …, 2020
Flash-decoding for long-context inference
T Dao, D Haziza, F Massa, G Sizov
Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on aerial lidar
J Tolan, HI Yang, B Nosarzewski, G Couairon, HV Vo, J Brandt, J Spore, ...
Remote Sensing of Environment 300, 113888, 2024
Alzheimer classification with MR images: Exploration of CNN performance factors
V Wegmayr, D Haziza
Sub-meter resolution canopy height maps using self-supervised learning and a vision transformer trained on Aerial and GEDI Lidar
J Tolan, HI Yang, B Nosarzewski, G Couairon, H Vo, J Brandt, J Spore, ...
arXiv e-prints, arXiv: 2304.07213, 2023
HiPlot-High dimensional Interactive Plotting
D Haziza, J Rapin, G Synnaeve
Systems and method for low bandwidth video-chat compression
MM Oquab, P Stock, O Gafni, DRD Haziza, T Xu, P Zhang, O Çelebi, ...
US Patent App. 17/224,103, 2022
Growing Up Together: Structured Exploration for Large Action Spaces
G Synnaeve, J Gehring, Z Lin, D Haziza, N Usunier, D Rothermel, V Mella, ...
Efficient conditioned face animation using frontally-viewed embedding
M Oquab, D Haziza, L Schwartz, T Xu, K Zand, R Wang, P Liu, C Couprie
arXiv preprint arXiv:2203.08765, 2022
Population Based Training for Data Augmentation and Regularization in Speech Recognition
D Haziza, J Rapin, G Synnaeve
arXiv preprint arXiv:2010.03899, 2020
ROMUL: Scale Adaptative Population Based Training
D HAZIZA, J Rapin, G Synnaeve
The system can't perform the operation now. Try again later.
Articles 1–17