no code implementations • 31 Jan 2024 • Thibaut Menes, Olivier Risser-Maroix
Model Soups, extending Stochastic Weights Averaging (SWA), combine models fine-tuned with different hyperparameters.
no code implementations • 15 Jun 2023 • Nicolas Bizzozzero, Ihab Bendidi, Olivier Risser-Maroix
The ability to predict the performance of a query before results are returned has been a longstanding challenge in Information Retrieval (IR) systems.
no code implementations • 18 Oct 2022 • Benjamin Chamand, Olivier Risser-Maroix, Camille Kurtz, Philippe Joly, Nicolas Loménie
Temperature is a widely used hyperparameter in various tasks involving neural networks, such as classification or metric learning, whose choice can have a direct impact on the model performance.
no code implementations • 2 Aug 2022 • Olivier Risser-Maroix, Benjamin Chamand
The formula discovered on more than 260 datasets of embeddings has a Pearson's correlation of 0. 96 and a $r^2$ of 0. 93.
1 code implementation • 3 Jun 2022 • Olivier Risser-Maroix, Amine Marzouki, Hala Djeghim, Camille Kurtz, Nicolas Lomenie
As a consequence, such features are powerful to compare semantically related images but not really efficient to compare images visually similar but semantically unrelated.