no code implementations • 15 Feb 2023 • Aude Sportisse, Hugo Schmutz, Olivier Humbert, Charles Bouveyron, Pierre-Alexandre Mattei
Semi-supervised learning is a powerful technique for leveraging unlabeled data to improve machine learning models, but it can be affected by the presence of ``informative'' labels, which occur when some classes are more likely to be labeled than others.
2 code implementations • 14 Mar 2022 • Hugo Schmutz, Olivier Humbert, Pierre-Alexandre Mattei
Our debiasing approach is straightforward to implement and applicable to most deep SSL methods.
no code implementations • 2 Mar 2022 • Federico Bergamin, Pierre-Alexandre Mattei, Jakob D. Havtorn, Hugo Senetaire, Hugo Schmutz, Lars Maaløe, Søren Hauberg, Jes Frellsen
These techniques, based on classical statistical tests, are model-agnostic in the sense that they can be applied to any differentiable generative model.