# Calibration of Model Uncertainty for Dropout Variational Inference

arXiv: https://arxiv.org/abs/2006.11584 · HTML: https://mlsanity.com/paper/2006.11584/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2020.

## Built on by (most cited first, 18 of 18)

- [NP-Match: When Neural Processes meet Semi-Supervised Learning](https://mlsanity.com/paper/2207.01066/) (2022)
- [BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks](https://mlsanity.com/paper/2207.06873/) (2022)
- [Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression](https://mlsanity.com/paper/2308.09065/) (2023)
- [On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models](https://mlsanity.com/paper/2510.09008/) (2025)
- [Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review](https://mlsanity.com/paper/2504.18346/) (2025)
- [Uncertainty quantification with approximate variational learning for wearable photoplethysmography prediction tasks](https://mlsanity.com/paper/2505.11412/) (2025)
- [Autoencoder Attractors for Uncertainty Estimation](https://mlsanity.com/paper/2204.00382/) (2022)
- [NP-Match: Towards a New Probabilistic Model for Semi-Supervised Learning](https://mlsanity.com/paper/2301.13569/) (2023)
- [An Uncertainty Aided Framework for Learning based Liver T1ρ Mapping and Analysis](https://mlsanity.com/paper/2307.02736/) (2023)
- [HypUC: Hyperfine Uncertainty Calibration with Gradient-boosted Corrections for Reliable Regression on Imbalanced Electrocardiograms](https://mlsanity.com/paper/2311.13821/) (2023)
- [Deep Neural Network Calibration by Reducing Classifier Shift with Stochastic Masking](https://mlsanity.com/paper/2508.09116/) (2025)
- [Federated Learning via Meta-Variational Dropout](https://mlsanity.com/paper/2510.20225/) (2025)
- [Weight Pruning and Uncertainty in Radio Galaxy Classification](https://mlsanity.com/paper/2111.11654/) (2021)
- [Improving the Behaviour of Vision Transformers with Token-consistent Stochastic Layers](https://mlsanity.com/paper/2112.15111/) (2021)
- [Exploring Probabilistic Models for Semi-supervised Learning](https://mlsanity.com/paper/2404.04199/) (2024)
- [Uncertainty-aware Test-Time Training (UT3) for Efficient On-the-fly Domain Adaptive Dense Regression](https://mlsanity.com/paper/2509.03012/) (2025)
- [Adaptive Individual Uncertainty under Out-Of-Distribution Shift with Expert-Routed Conformal Prediction](https://mlsanity.com/paper/2510.15233/) (2025)
- [CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Model](https://mlsanity.com/paper/2603.10745/) (2026)

## 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.