1 code implementation • 23 Apr 2022 • Adrien Courtois, Jean-Michel Morel, Pablo Arias
It is therefore impossible to know what cues a given neural structure is taking advantage of in such data.
no code implementations • 7 Nov 2022 • Adrien Courtois, Jean-Michel Morel, Pablo Arias
In particular, what are the interpolation capabilities of trained neural networks?
no code implementations • 18 Nov 2022 • Ahmed Ben Saad, Kristina Prokopetc, Josselin Kherroubi, Axel Davy, Adrien Courtois, Gabriele Facciolo
In this paper we will focus on the depth information, which can be obtained by using a depth estimation network or measured from available data (stereovision, parallax motion, LiDAR, etc.).
1 code implementation • 25 May 2023 • Adrien Courtois, Damien Scieur, Jean-Michel Morel, Pablo Arias, Thomas Eboli
We propose SING (StabIlized and Normalized Gradient), a plug-and-play technique that improves the stability and generalization of the Adam(W) optimizer.