3 papers
eess.IV2022
Learning Neural Optimal Interpolation Models and Solvers
Maxime Beauchamp, Joseph Thompson, Hugo Georgenthum +2
The reconstruction of gap-free signals from observation data is a critical challenge for numerous application domains, such as geoscience and space-based earth observation, when th…
eess.IV2022
4DVarNet-SSH: end-to-end learning of variational interpolation schemes for nadir and wide-swath satellite altimetry
Maxime Beauchamp, Quentin Febvre, Hugo Georgentum +1
The reconstruction of sea surface currents from satellite altimeter data is a key challenge in spatial oceanography, especially with the upcoming wide-swath SWOT (Surface Ocean and…
cs.CV2019
Reversible designs for extreme memory cost reduction of CNN training
Tristan Hascoet, Quentin Febvre, Yasuo Ariki +1
Training Convolutional Neural Networks (CNN) is a resource intensive task that requires specialized hardware for efficient computation. One of the most limiting bottleneck of CNN t…