AI Paper Atlas

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

Multi-Source Neural Variational Inference

Richard Kurle, Stephan Günnemann, Patrick van der Smagt

AAAI 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Structured latent VAEs · 24 citations (OpenAlex)

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
integrate redundant noisy sources using the hybrid elboac objectiveMSNVI · MNIST-NOnegative ELBO: 94.95 -> 92.21Improved
use K=1 instead of K=16 (ablation)MSNVI elboac · MNIST-TBnegative ELBO: 90.07 -> 90.81Hurt
use K=1 instead of K=16 (ablation)MSNVI elboac · MNIST-QUnegative ELBO: 89.20 -> 90.17Hurt
use K=1 instead of K=16 (ablation)MSNVI elboac · MNIST-NOnegative ELBO: 92.21 -> 94.49Hurt
learn individual source beliefs, then integrate them with a product of expertsMSNVI · MNIST-TBnegative ELBO (elboa evaluation): 102.20 -> 94.38Improved
learn individual source beliefs, then integrate them with a product of expertsMSNVI · MNIST-QUnegative ELBO (elboa evaluation): 120.46 -> 108.07Improved
learn the generative model for segmentation only while retaining all inference sources (ablation)MSNVI elboa · Caltech-UCSD Birds 200segmentation accuracy: 0.808 -> 0.870Improved
learn the generative model for segmentation only while retaining all inference sources (ablation)MSNVI elboac · Caltech-UCSD Birds 200segmentation accuracy: 0.810 -> 0.872Improved
learn generative models for both images and segmentations rather than segmentation only (ablation)MSNVI elboa · Caltech-UCSD Birds 200segmentation accuracy: 0.870 -> 0.808Hurt
learn generative models for both images and segmentations rather than segmentation only (ablation)MSNVI elboac · Caltech-UCSD Birds 200segmentation accuracy: 0.872 -> 0.810Hurt
integrate beliefs from redundant sensorsMSNVI pendulum inference · Pendulumpredictive uncertaintyImproved
detect a failed sensor using belief conflict and exclude it from integrationMSNVI pendulum inference · Pendulumrobustness to sensor failureImproved

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