mlsanityData to 7 Oct 2026

Calibration of Model Uncertainty for Dropout Variational Inference

arXiv 2006.11584 ↗First posted 20 Jun 2020cs.LG stat.MLcited by 18

Not on the map. Why?

Abstract (arXiv)

The model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. In this paper, different logit scaling methods are extended to dropout variational inference to recalibrate model uncertainty. Expected uncertainty calibration error (UCE) is presented as a metric to measure miscalibration. The effectiveness of recalibration is evaluated on CIFAR-10/100 and SVHN for recent CNN architectures. Experimental results show that logit scaling considerably reduce miscalibration by means of UCE. Well-calibrated uncertainty enables reliable rejection of uncertain predictions and robust detection of out-of-distribution data.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 3; 2023: 4; 2024: 1; 2025: 7; 2026: 1.

18 papers.

Sort:

By area:

  1. 2022NP-Match: When Neural Processes meet Semi-Supervised Learningcited by 25
  2. 2022BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networkscited by 23
  3. 2023Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regressioncited by 7
  4. 2025On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Modelscited by 4
  5. 2025Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Reviewcited by 3
  6. 2025Uncertainty quantification with approximate variational learning for wearable photoplethysmography prediction taskscited by 3
  7. 2022Autoencoder Attractors for Uncertainty Estimationcited by 2
  8. 2023NP-Match: Towards a New Probabilistic Model for Semi-Supervised Learningcited by 1
  9. 2023An Uncertainty Aided Framework for Learning based Liver T1ρ Mapping and Analysiscited by 1
  10. 2023HypUC: Hyperfine Uncertainty Calibration with Gradient-boosted Corrections for Reliable Regression on Imbalanced Electrocardiogramscited by 1
  11. 2025Deep Neural Network Calibration by Reducing Classifier Shift with Stochastic Maskingcited by 1
  12. 2025Federated Learning via Meta-Variational Dropoutcited by 1
6 more
  1. 2021Weight Pruning and Uncertainty in Radio Galaxy Classificationcited by 0
  2. 2021Improving the Behaviour of Vision Transformers with Token-consistent Stochastic Layerscited by 0
  3. 2024Exploring Probabilistic Models for Semi-supervised Learningcited by 0
  4. 2025Uncertainty-aware Test-Time Training (UT3) for Efficient On-the-fly Domain Adaptive Dense Regressioncited by 0
  5. 2025Adaptive Individual Uncertainty under Out-Of-Distribution Shift with Expert-Routed Conformal Predictioncited by 0
  6. 2026CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Modelcited by 0