mlsanityData to 7 Oct 2026

Credal Wrapper of Model Averaging for Uncertainty Estimation in Classification

arXiv 2405.15047 ↗First posted 23 May 2024cs.LG cs.AIcited by 13

Not on the map. Why?

Abstract (arXiv)

This paper presents an innovative approach, called credal wrapper, to formulating a credal set representation of model averaging for Bayesian neural networks (BNNs) and deep ensembles (DEs), capable of improving uncertainty estimation in classification tasks. Given a finite collection of single predictive distributions derived from BNNs or DEs, the proposed credal wrapper approach extracts an upper and a lower probability bound per class, acknowledging the epistemic uncertainty due to the availability of a limited amount of distributions. Such probability intervals over classes can be mapped on a convex set of probabilities (a credal set) from which, in turn, a unique prediction can be obtained using a transformation called intersection probability transformation. In this article, we conduct extensive experiments on several out-of-distribution (OOD) detection benchmarks, encompassing various dataset pairs (CIFAR10/100 vs SVHN/Tiny-ImageNet, CIFAR10 vs CIFAR10-C, CIFAR100 vs CIFAR100-C and ImageNet vs ImageNet-O) and using different network architectures (such as VGG16, ResNet-18/50, EfficientNet B2, and ViT Base). Compared to the BNN and DE baselines, the proposed credal wrapper method exhibits superior performance in uncertainty estimation and achieves a lower expected calibration error on corrupted data.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 46 of its 87 references that are in the map. First posted on arXiv 23 May 2024.

Builds on

46 of 87 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  8. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  9. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  10. 2019Natural Adversarial Examplescited by 1,401
  11. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  12. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
34 more
  1. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  2. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  3. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  4. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  5. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
  6. 2019Measuring Calibration in Deep Learningcited by 443
  7. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  8. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  9. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 336
  10. 2017Variational Dropout Sparsifies Deep Neural Networkscited by 265
  11. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  12. 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
  13. 2020Efficient and Scalable Bayesian Neural Nets with Rank-1 Factorscited by 171
  14. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 163
  15. 2019Ensemble Distribution Distillationcited by 158
  16. 2018Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batchescited by 133
  17. 2019Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustnesscited by 104
  18. 2019DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networkscited by 92
  19. 2020Bayesian Deep Ensembles via the Neural Tangent Kernelcited by 90
  20. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  21. 2017Bayesian Hypernetworkscited by 64
  22. 2022Deep Ensembles Work, But Are They Necessary?cited by 63
  23. 2020All You Need is a Good Functional Prior for Bayesian Deep Learningcited by 61
  24. 2022Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Taskscited by 49
  25. 2023Credal Bayesian Deep Learningcited by 45
  26. 2023Tractable Function-Space Variational Inference in Bayesian Neural Networkscited by 41
  27. 2023Is the Volume of a Credal Set a Good Measure for Epistemic Uncertainty?cited by 40
  28. 2024Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?cited by 34
  29. 2020Fast Predictive Uncertainty for Classification with Bayesian Deep Networkscited by 31
  30. 2024CreINNs: Credal-Set Interval Neural Networks for Uncertainty Estimation in Classification Taskscited by 26
  31. 2021Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous Vehiclescited by 24
  32. 2021Ensemble-based Uncertainty Quantification: Bayesian versus Credal Inferencecited by 16
  33. 2023Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noisecited by 15
  34. 2022The intersection probability: betting with probability intervalscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 8.

13 papers.

Sort:

  1. 2025Integral Imprecise Probability Metricscited by 11
  2. 2026Learning Credal Ensembles via Distributionally Robust Optimizationcited by 6
  3. 2026Quantifying Epistemic Predictive Uncertainty in Conformal Predictioncited by 4
  4. 2025Optimal Conformal Prediction under Epistemic Uncertaintycited by 3
  5. 2026Quantification of Credal Uncertainty: A Distance-Based Approachcited by 2
  6. 2026Credal Large Language Models for Semantic Commitment under Uncertaintycited by 2
  7. 2025Cooperative Variance Estimation and Bayesian Neural Networks for Disentangling Aleatoric and Epistemic Uncertaintiescited by 1
  8. 2025Last Layer Hamiltonian Monte Carlocited by 1
  9. 2026Set-based v.s. Distribution-based Representations of Epistemic Uncertainty: A Comparative Studycited by 1
  10. 2025PEARL: Performance-Enhanced Aggregated Representation Learningcited by 0
  11. 2026Efficient Credal Prediction through Decalibrationcited by 0
  12. 2026Evidential Rule Learning for Interpretable Classification with Abstentioncited by 0
1 more
  1. 2026XU-RS: Explaining Credal Width in Random-Set Language Modelscited by 0