mlsanityData to 7 Oct 2026

Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference

arXiv 1909.13550 ↗First posted 30 Sep 2019cs.LG stat.MLcited by 35

Not on the map. Why?

Abstract (arXiv)

Model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. The uncertainty does not represent the model error well. In this paper, temperature scaling is extended to dropout variational inference to calibrate model uncertainty. Expected uncertainty calibration error (UCE) is presented as a metric to measure miscalibration of uncertainty. The effectiveness of this approach is evaluated on CIFAR-10/100 for recent CNN architectures. Experimental results show, that temperature scaling considerably reduces miscalibration by means of UCE and enables robust rejection of uncertain predictions. The proposed approach can easily be derived from frequentist temperature scaling and yields well-calibrated model uncertainty. It is simple to implement and does not affect the model accuracy.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 3; 2023: 8; 2024: 7; 2025: 8; 2026: 2.

35 papers.

Sort:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  2. 2023Calibration in Deep Learning: A Survey of the State-of-the-Artcited by 72
  3. 2021Spatially Varying Label Smoothing: Capturing Uncertainty from Expert Annotationscited by 31
  4. 2022Towards Improving Calibration in Object Detection Under Domain Shiftcited by 26
  5. 2022BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networkscited by 23
  6. 2021Class-Distribution-Aware Calibration for Long-Tailed Visual Recognitioncited by 19
  7. 2021Recalibration of Aleatoric and Epistemic Regression Uncertainty in Medical Imagingcited by 18
  8. 2024A Survey on Safe Multi-Modal Learning Systemcited by 15
  9. 2023Cal-DETR: Calibrated Detection Transformercited by 11
  10. 2022On Calibrated Model Uncertainty in Deep Learningcited by 7
  11. 2024Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimationcited by 7
  12. 2023Overcoming the Limitations of Localization Uncertainty: Efficient & Exact Non-Linear Post-Processing and Calibrationcited by 5
23 more
  1. 2025Revisiting Gradient-based Uncertainty for Monocular Depth Estimationcited by 5
  2. 2021Posterior Temperature Optimization in Variational Inference for Inverse Problemscited by 3
  3. 2024Decoupling of neural network calibration measurescited by 3
  4. 2025Enhancing Uncertainty Estimation in Semantic Segmentation via Monte-Carlo Frequency Dropoutcited by 3
  5. 2025Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Reviewcited by 3
  6. 2023Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurementcited by 2
  7. 2024Evaluating Bayesian deep learning for radio galaxy classificationcited by 2
  8. 2025CLUE: Neural Networks Calibration via Learning Uncertainty-Error alignmentcited by 2
  9. 2025h-calibration: Rethinking Classifier Recalibration with Probabilistic Error-Bounded Objectivecited by 2
  10. 2021Unsupervised Model Drift Estimation with Batch Normalization Statistics for Dataset Shift Detection and Model Selectioncited by 1
  11. 2023Towards Unbiased Calibration using Meta-Regularizationcited by 1
  12. 2023An Uncertainty Aided Framework for Learning based Liver T1ρ Mapping and Analysiscited by 1
  13. 2023On Calibration of Modern Quantized Efficient Neural Networkscited by 1
  14. 2024Improving Uncertainty-Error Correspondence in Deep Bayesian Medical Image Segmentationcited by 1
  15. 2024A Deep Learning Approach to Estimate Canopy Height and Uncertainty by Integrating Seasonal Optical, SAR and Limited GEDI LiDAR Data over Northern Forestscited by 1
  16. 2026Extending confidence calibration to generalised measures of variationcited by 1
  17. 2021TransMorph: Transformer for unsupervised medical image registrationcited by 0
  18. 2023Rethinking Soft Label in Label Distribution Learning Perspectivecited by 0
  19. 2024Dual-Channel Reliable Breast Ultrasound Image Classification Based on Explainable Attribution and Uncertainty Quantificationcited by 0
  20. 2025Are you SURE? Enhancing Multimodal Pretraining with Missing Modalities through Uncertainty Estimationcited by 0
  21. 2025MMformer with Adaptive Transferable Attention: Advancing Multivariate Time Series Forecasting for Environmental Applicationscited by 0
  22. 2025Uncertainty in Semantic Language Modeling with PIXELScited by 0
  23. 2026Confidence-Uncertainty Boundary Calibration for Bayesian Deep Learning in Medical Image Analysiscited by 0