AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Remedying Uncertainty Representations in Visual Inference Through Explaining-Away Variational Autoencoders

Josefina Catoni, Domonkos Martos, Ferenc Csikor, Enzo Ferrante, Diego Humberto Milone, Balazs Meszena, Gergő Orbán, Rodrigo Echeveste

TPAMI 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Regularizing VAE latent information

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add a global multiplicative scaling latent s (EA-VAE)standard VAE · natural image patchesposterior noise variance vs contrastImproved
add scaling latent sstandard VAE · cMNIST and cFashionMNISTsignal mean saturation with contrastImproved
add scaling latent sstandard VAE · MNIST morphing, 45 digit pairscentral uncertainty maximum: 31%Improved
replace single-sample ELBO with multi-sample IWAE objective (ablation)standard VAE · natural image patchescontrast-dependence of posterior varianceNo clear effect
add MC Dropout at inference (ablation)standard VAE · morphing and OOD experimentsuncertainty estimatesNo clear effect
add scaling latent sstandard VAE · Chest X-ray blur and noise corruptionlatent uncertaintyImproved
add scaling latent sstandard VAE · MNIST/ChestMNIST OOD, downstream MLPpredictive entropy: p < 10^-15Improved
use lognormal or gamma posterior for s instead of softplus-Laplace (ablation)EA-VAE · natural image patchesqualitative uncertainty behaviourNo clear effect
add scaling latent sstandard VAE · training time on natural image patcheshours: 62.2 -> 67Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy