Continual Evidential Deep Learning for Out-of-Distribution Detection
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 …
ability to provide accurate and reliable predictions. Evidential deep learning stands out …
incdfm: Incremental deep feature modeling for continual novelty detection
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 …
models operate in non-stationary conditions and are repeatedly exposed to new, unseen …
OOD Aware Supervised Contrastive Learning
S Seifi, DO Reino, N Chumerin… - Proceedings of the …, 2024 - openaccess.thecvf.com
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 …
machine learning models identifying samples that fall outside of the training distribution, ie in …
Statistical Context Detection for Deep Lifelong Reinforcement Learning
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 …
different tasks. Task labels are used in lifelong learning algorithms to perform consolidation …
Incremental Object-Based Novelty Detection with Feedback Loop
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 …
classes seen during training by an object detection model. The task is particularly crucial in …
Apprentissage continu et étiquetage automatique de données pour améliorer un réseau de neurones incertain
Q Christoffel, A Ayadi, A Deruyver… - … Rencontres des Jeunes …, 2022 - hal.science
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 …
sont encore très loin d'imiter le comportement humain. Cet article propose nos premières …