3 papers
cs.LG2023
A Practical Approach to Novel Class Discovery in Tabular Data
Colin Troisemaine, Alexandre Reiffers-Masson, Stéphane Gosselin +2
The problem of Novel Class Discovery (NCD) consists in extracting knowledge from a labeled set of known classes to accurately partition an unlabeled set of novel classes. While NCD…
cs.LG2023
An Interactive Interface for Novel Class Discovery in Tabular Data
Colin Troisemaine, Joachim Flocon-Cholet, Stéphane Gosselin +3
Novel Class Discovery (NCD) is the problem of trying to discover novel classes in an unlabeled set, given a labeled set of different but related classes. The majority of NCD method…
stat.ML2020
On the Variational Posterior of Dirichlet Process Deep Latent Gaussian Mixture Models
Amine Echraibi, Joachim Flocon-Cholet, Stéphane Gosselin +1
Thanks to the reparameterization trick, deep latent Gaussian models have shown tremendous success recently in learning latent representations. The ability to couple them however wi…