Uncertainty-based deep learning models have attracted a great deal of interest for their
ability to provide accurate and reliable predictions. Evidential deep learning stands out …

Novelty detection is a key capability for practical machine learning in the real world, where
models operate in non-stationary conditions and are repeatedly exposed to new, unseen …

Abstract Out-of-Distribution (OOD) detection is a crucial problem for the safe deployment of
machine learning models identifying samples that fall outside of the training distribution, ie in …

Context detection involves labeling segments of an online stream of data as belonging to
different tasks. Task labels are used in lifelong learning algorithms to perform consolidation …

Object-based Novelty Detection (ND) aims to identify unknown objects that do not belong to
classes seen during training by an object detection model. The task is particularly crucial in …

Les réseaux de neurones artificiels s' inspirent du fonctionnement du cerveau humain, mais
sont encore très loin d'imiter le comportement humain. Cet article propose nos premières …