mlsanityData to 7 Oct 2026

A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges

arXiv 2011.06225 ↗First posted 12 Nov 2020cs.LG cs.AI cs.CVcited by 813

Not on the map. Why?

Abstract (arXiv)

Uncertainty quantification (UQ) plays a pivotal role in reduction of uncertainties during both optimization and decision making processes. It can be applied to solve a variety of real-world applications in science and engineering. Bayesian approximation and ensemble learning techniques are two most widely-used UQ methods in the literature. In this regard, researchers have proposed different UQ methods and examined their performance in a variety of applications such as computer vision (e.g., self-driving cars and object detection), image processing (e.g., image restoration), medical image analysis (e.g., medical image classification and segmentation), natural language processing (e.g., text classification, social media texts and recidivism risk-scoring), bioinformatics, etc. This study reviews recent advances in UQ methods used in deep learning. Moreover, we also investigate the application of these methods in reinforcement learning (RL). Then, we outline a few important applications of UQ methods. Finally, we briefly highlight the fundamental research challenges faced by UQ methods and discuss the future research directions in this field.

Key facts. Cited by 813 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 65; 2022: 128; 2023: 189; 2024: 188; 2025: 159; 2026: 84.

813 papers.

Sort:

By area:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  2. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  3. 2021Diffusion Models for Implicit Image Segmentation Ensemblescited by 198
  4. 2022Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisonscited by 169
  5. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  6. 2024Benchmarking LLMs via Uncertainty Quantificationcited by 124
  7. 2021Mutual Consistency Learning for Semi-supervised Medical Image Segmentationcited by 107
  8. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  9. 2022Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysiscited by 104
  10. 2023A Brief Review of Hypernetworks in Deep Learningcited by 102
  11. 2023Bayes' Rays: Uncertainty Quantification for Neural Radiance Fieldscited by 90
  12. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 89
38 more
  1. 2022A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglementcited by 87
  2. 2021Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representationscited by 80
  3. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 79
  4. 2023Uncertainty Quantification over Graph with Conformalized Graph Neural Networkscited by 79
  5. 2023A Survey on Uncertainty Quantification Methods for Deep Learningcited by 78
  6. 2024LLMs Will Always Hallucinate, and We Need to Live With Thiscited by 77
  7. 2023Machine learning with data assimilation and uncertainty quantification for dynamical systems: a reviewcited by 74
  8. 2024Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approachcited by 73
  9. 2024From PINNs to PIKANs: Recent Advances in Physics-Informed Machine Learningcited by 73
  10. 2024Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknowncited by 71
  11. 2022Do Bayesian Neural Networks Need To Be Fully Stochastic?cited by 63
  12. 2022Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysiscited by 62
  13. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  14. 2023Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulationcited by 60
  15. 2023A Review of Uncertainty Estimation and its Application in Medical Imagingcited by 59
  16. 2022Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fieldscited by 58
  17. 2024Aligning Language Models to Explicitly Handle Ambiguitycited by 55
  18. 2024SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Modelscited by 54
  19. 2022Assaying Out-Of-Distribution Generalization in Transfer Learningcited by 53
  20. 2023Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Taskscited by 53
  21. 2021Improving black-box optimization in VAE latent space using decoder uncertaintycited by 51
  22. 2021Trustworthy Long-Tailed Classificationcited by 51
  23. 2021Learning to Map for Active Semantic Goal Navigationcited by 47
  24. 2023Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4cited by 45
  25. 2024Uncertainty Quantification for In-Context Learning of Large Language Modelscited by 45
  26. 2022Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimationcited by 43
  27. 2023PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awarenesscited by 42
  28. 2021Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributionscited by 39
  29. 2024BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcutscited by 36
  30. 2023When Does Optimizing a Proper Loss Yield Calibration?cited by 35
  31. 2024Conformal Prediction Sets Improve Human Decision Makingcited by 35
  32. 2022Invariant Feature Learning for Generalized Long-Tailed Classificationcited by 34
  33. 2022A System-Level View on Out-of-Distribution Data in Roboticscited by 33
  34. 2023Topology-Aware Uncertainty for Image Segmentationcited by 32
  35. 2022DeepONet-Grid-UQ: A Trustworthy Deep Operator Framework for Predicting the Power Grid's Post-Fault Trajectoriescited by 30
  36. 2023Active Neural Mappingcited by 30
  37. 2024Review of multimodal machine learning approaches in healthcarecited by 30
  38. 2022A review of predictive uncertainty estimation with machine learningcited by 29

50 most cited of 813 All 813 (JSON)