AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Sampling-Free Epistemic Uncertainty Estimation Using Approximated Variance Propagation

Janis Postels, Francesco Ferroni, Huseyin Coskun, Nassir Navab, Federico Tombari

ICCV 2019 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Single-model predictive uncertainty · 150 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
replace MC dropout sampling with analytic variance propagationMC dropout · UCI regression (9 datasets)Test log-likelihood: -2.55 -> -2.65 (Boston), 4.36 -> 3.64 (Naval), -2.32 -> -2.10 (Yacht)Mixed
replace MC dropout sampling with analytic variance propagationMC dropout · UCI regression (9 datasets)Test RMSE: 3.06 -> 3.13 (Boston), 2.89 -> 3.14 (Yacht)No clear effect
replace MC dropout sampling with analytic variance propagationMC dropout · UCI regression (9 datasets)Runtime [s]: 3.47 -> 0.06 (Boston)Improved
use diagonal covariance for ENCDEC architecture where dropout is far from outputVariance propagation · CamVid (Bayesian SegNet ENCDEC)uncertainty magnitude: mean absolute difference 93.7% of MC mean varianceHurt
replace MC dropout with variance propagationBayesian SegNet · CamVidMean IoU: 63.1 -> 54.1Hurt

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