Combining pre-trained Vision Transformers and CIDER for Out Of Domain Detection

no code implementations • 6 Sep 2023 • Grégor Jouet, Clément Duhart, Francis Rousseaux, Julio Laborde, Cyril de Runz

Out-of-domain (OOD) detection is a crucial component in industrial applications as it helps identify when a model encounters inputs that are outside the training distribution.

Your most telling friends: Propagating latent ideological features on Twitter using neighborhood coherence

no code implementations • 12 Mar 2021 • Pedro Ramaciotti Morales, Jean-Philippe Cointet, Julio Laborde

Ideological scaling for users in social networks such as Twitter is an example, but similar settings can include diverse applications in other networks and even media platforms or e-commerce.