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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace MC dropout sampling with analytic variance propagation | MC 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 propagation | MC 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 propagation | MC dropout · UCI regression (9 datasets) | Runtime [s]: 3.47 -> 0.06 (Boston) | Improved |
| use diagonal covariance for ENCDEC architecture where dropout is far from output | Variance propagation · CamVid (Bayesian SegNet ENCDEC) | uncertainty magnitude: mean absolute difference 93.7% of MC mean variance | Hurt |
| replace MC dropout with variance propagation | Bayesian SegNet · CamVid | Mean IoU: 63.1 -> 54.1 | Hurt |
Closest papers by meaning
- On the Practicality of Deterministic Epistemic Uncertainty (ICML 2022 · similarity 0.91)
- Epistemic Uncertainty Quantification For Pre-Trained Neural Networks (CVPR 2024 · similarity 0.90)
- Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage? (NeurIPS 2024 · similarity 0.88)
- SURE: SUrvey REcipes for building reliable and robust deep networks (CVPR 2024 · similarity 0.87)
- Adaptive Sampling to Reduce Epistemic Uncertainty Using Prediction Interval-Generation Neural Networks (AAAI 2025 · similarity 0.87)
- Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods? (ICML 2024 · similarity 0.87)
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.
