no code implementations • 23 Mar 2023 • Kilian Zepf, Selma Wanna, Marco Miani, Juston Moore, Jes Frellsen, Søren Hauberg, Aasa Feragen, Frederik Warburg
To ensure robustness to such incorrect segmentations, we propose Laplacian Segmentation Networks (LSN) that jointly model epistemic (model) and aleatoric (data) uncertainty in image segmentation.
1 code implementation • 30 Jun 2022 • Marco Miani, Frederik Warburg, Pablo Moreno-Muñoz, Nicke Skafte Detlefsen, Søren Hauberg
In this work, we present a Bayesian autoencoder for unsupervised representation learning, which is trained using a novel variational lower-bound of the autoencoder evidence.
no code implementations • 29 Jun 2021 • Marco Miani, Maurizio Parton, Marco Romito
These bounds can be used to prove PAC convergence and sample efficiency results when a PAC optimizer is plugged in Curious Explorer.