mlsanityData to 7 Oct 2026

Predictive Uncertainty Estimation via Prior Networks

arXiv 1802.10501 ↗First posted 28 Feb 2018stat.ML cs.LGcited by 555

Not on the map. Why?

Abstract (arXiv)

Estimating how uncertain an AI system is in its predictions is important to improve the safety of such systems. Uncertainty in predictive can result from uncertainty in model parameters, irreducible data uncertainty and uncertainty due to distributional mismatch between the test and training data distributions. Different actions might be taken depending on the source of the uncertainty so it is important to be able to distinguish between them. Recently, baseline tasks and metrics have been defined and several practical methods to estimate uncertainty developed. These methods, however, attempt to model uncertainty due to distributional mismatch either implicitly through model uncertainty or as data uncertainty. This work proposes a new framework for modeling predictive uncertainty called Prior Networks (PNs) which explicitly models distributional uncertainty. PNs do this by parameterizing a prior distribution over predictive distributions. This work focuses on uncertainty for classification and evaluates PNs on the tasks of identifying out-of-distribution (OOD) samples and detecting misclassification on the MNIST dataset, where they are found to outperform previous methods. Experiments on synthetic and MNIST and CIFAR-10 data show that unlike previous non-Bayesian methods PNs are able to distinguish between data and distributional uncertainty.

Key facts. Cited by 555 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 80; 2022: 96; 2023: 102; 2024: 119; 2025: 90; 2026: 68.

555 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  3. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  4. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  5. 2021Revisiting the Calibration of Modern Neural Networkscited by 387
  6. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  7. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  8. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  9. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  10. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  11. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  12. 2022Trusted Multi-View Classification with Dynamic Evidential Fusioncited by 167
38 more
  1. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  2. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  3. 2023Non-Parametric Outlier Synthesiscited by 129
  4. 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 124
  5. 2021Epistemic Neural Networkscited by 120
  6. 2023Decomposing Uncertainty for Large Language Models through Input Clarification Ensemblingcited by 113
  7. 2021Pixel-wise Anomaly Detection in Complex Driving Scenescited by 109
  8. 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 102
  9. 2021Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Taskscited by 100
  10. 2021Evidential Deep Learning for Open Set Action Recognitioncited by 96
  11. 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Surveycited by 93
  12. 2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87
  13. 2022Training OOD Detectors in their Natural Habitatscited by 86
  14. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  15. 2023Provable Dynamic Fusion for Low-Quality Multimodal Datacited by 81
  16. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 79
  17. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  18. 2023A Survey on Uncertainty Quantification Methods for Deep Learningcited by 78
  19. 2021Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentationcited by 77
  20. 2023Dream the Impossible: Outlier Imagination with Diffusion Modelscited by 77
  21. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  22. 2022Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantificationcited by 71
  23. 2024VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimationcited by 71
  24. 2021Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detectioncited by 67
  25. 2022RbA: Segmenting Unknown Regions Rejected by Allcited by 67
  26. 2022Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisationcited by 65
  27. 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generationcited by 65
  28. 2022Deep Ensembles Work, But Are They Necessary?cited by 63
  29. 2021Understanding Softmax Confidence and Uncertaintycited by 62
  30. 2023Uncertainty Estimation by Fisher Information-based Evidential Deep Learningcited by 58
  31. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  32. 2024A Survey of Uncertainty Estimation in LLMs: Theory Meets Practicecited by 54
  33. 2022A Call to Reflect on Evaluation Practices for Failure Detection in Image Classificationcited by 51
  34. 2022A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awarenesscited by 49
  35. 2022Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Taskscited by 49
  36. 2022Sample-dependent Adaptive Temperature Scaling for Improved Calibrationcited by 48
  37. 2022On Uncertainty, Tempering, and Data Augmentation in Bayesian Classificationcited by 46
  38. 2023Uncertainty in Natural Language Processing: Sources, Quantification, and Applicationscited by 44

50 most cited of 555 All 555 (JSON)