no code implementations • 21 Mar 2023 • Gauthier Tallec, Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
The rising performance of deep neural networks is often empirically attributed to an increase in the available computational power, which allows complex models to be trained upon large amounts of annotated data.
no code implementations • 6 Mar 2023 • Gauthier Tallec, Arnaud Dapogny, Kevin Bailly
However, applying label smoothing as it is may aggravate imbalance-based pre-existing under-confidence issue and degrade performance.
no code implementations • 6 Aug 2022 • Gauthier Tallec, Jules Bonnard, Arnaud Dapogny, Kévin Bailly
From a learning point of view we use an uncertainty weighted loss for modelling the difference of stochasticity between the three tasks annotations.
no code implementations • 23 Mar 2022 • Gauthier Tallec, Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Action Unit (AU) Detection is the branch of affective computing that aims at recognizing unitary facial muscular movements.
no code implementations • 1 Feb 2022 • Gauthier Tallec, Arnaud Dapogny, Kevin Bailly
MONET uses a differentiable order selection to jointly learn task-wise modules with their optimal chaining order.