BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty

no code implementations • 12 Jul 2020 • Théo Guénais, Dimitris Vamvourellis, Yaniv Yacoby, Finale Doshi-Velez, Weiwei Pan

Traditional training of deep classifiers yields overconfident models that are not reliable under dataset shift.

Bayesian Inference