{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T22:59:38Z","timestamp":1773010778649,"version":"3.50.1"},"reference-count":196,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tpami.2025.3626645","type":"journal-article","created":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T17:33:50Z","timestamp":1761672830000},"page":"2476-2495","source":"Crossref","is-referenced-by-count":1,"title":["A Review of Uncertainty Representation and Quantification in Neural Networks"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8268-962X","authenticated-orcid":false,"given":"Kaizheng","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science, KU Leuven, Leuven, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9271-2130","authenticated-orcid":false,"given":"Fabio","family":"Cuzzolin","sequence":"additional","affiliation":[{"name":"School of Engineering, Computing and Mathematics, Oxford Brookes University, Oxford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7364-5382","authenticated-orcid":false,"given":"Keivan","family":"Shariatmadar","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, KU Leuven, Leuven, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5707-0160","authenticated-orcid":false,"given":"David","family":"Moens","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, KU Leuven, Leuven, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2623-9055","authenticated-orcid":false,"given":"Hans","family":"Hallez","sequence":"additional","affiliation":[{"name":"Department of Computer Science, KU Leuven, Leuven, Belgium"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3099164"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05946-3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2013.07.030"},{"key":"ref6","first-page":"5580","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Kendall","year":"2017"},{"key":"ref7","first-page":"1795","article-title":"Is the volume of a credal set a good measure for epistemic uncertainty?","volume-title":"Proc. 39th Conf. Uncertainty Artif. Intell.","author":"Sale","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107198"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20757"},{"key":"ref10","first-page":"79540","article-title":"Credal deep ensembles for uncertainty quantification","volume-title":"Proc. 38th Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2024"},{"key":"ref11","first-page":"1","article-title":"Credal wrapper of model averaging for uncertainty estimation in classification","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Wang","year":"2025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02336"},{"key":"ref13","first-page":"2204","article-title":"Learning from the wisdom of crowds by minimax entropy","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Zhou","year":"2012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITB.2010.2091144"},{"key":"ref15","first-page":"548","article-title":"Quantification of credal uncertainty in machine learning: A critical analysis and empirical comparison","volume-title":"Proc. Uncertainty Artif. Intell.","author":"H\u00fcllermeier","year":"2022"},{"key":"ref16","first-page":"3183","article-title":"Evidential deep learning to quantify classification uncertainty","volume-title":"proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Sensoy","year":"2018"},{"key":"ref17","first-page":"7047","article-title":"Predictive uncertainty estimation via prior networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Malinin","year":"2018"},{"key":"ref18","first-page":"14547","article-title":"Reverse KL-divergence training of prior networks: Improved uncertainty and adversarial robustness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Malinin","year":"2019"},{"key":"ref19","first-page":"1356","article-title":"Posterior network: Uncertainty estimation without OOD samples via density-based pseudo-counts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Charpentier","year":"2020"},{"key":"ref20","first-page":"1613","article-title":"Weight uncertainty in neural network","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blundell","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref22","article-title":"Bayesian hypernetworks","author":"Krueger","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-84854-x"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2022.3155327"},{"key":"ref25","first-page":"50972","article-title":"Benchmarking uncertainty disentanglement: Specialized uncertainties for specialized tasks","volume-title":"Proc. 38th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Mucs\u00e1nyi","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3083089"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/1475921720904543"},{"key":"ref28","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lakshminarayanan","year":"2017"},{"key":"ref29","first-page":"13991","article-title":"Can you trust your model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ovadia","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00167"},{"key":"ref31","first-page":"33646","article-title":"Deep ensembles work, but are they necessary?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Abe","year":"2022"},{"key":"ref32","first-page":"14927","article-title":"Deep evidential regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Amini","year":"2020"},{"key":"ref33","first-page":"1","article-title":"Natural posterior network: Deep bayesian predictive uncertainty for exponential family distributions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Charpentier","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/3468.833094"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.066"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02327-0"},{"key":"ref37","first-page":"1","article-title":"Random-set neural networks","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Manchingal","year":"2025"},{"key":"ref38","first-page":"116987","article-title":"Conformalized credal set predictors","volume-title":"Proc. 38th Adv. Neural Inf. Process. Syst.","author":"Javanmardi","year":"2024"},{"key":"ref39","first-page":"4075","article-title":"High-quality prediction intervals for deep learning: A distribution-free, ensembled approach","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pearce","year":"2018"},{"key":"ref40","first-page":"1179","article-title":"Prediction intervals: Split normal mixture from quality-driven deep ensembles","volume-title":"Proc. 36th Conf. Uncertainty Artif. Intell.","volume":"124","author":"Salem","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.084"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-021-02482-2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.02.005"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10562-9"},{"key":"ref45","first-page":"1","article-title":"Prior and posterior networks: A survey on evidential deep learning methods for uncertainty estimation","author":"Ulmer","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref46","article-title":"Sources of uncertainty in machine learning\u2013A statisticians\u2019 view","author":"Gruber","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.05.008"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1111\/insr.12502"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374138"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.58895\/ksp\/1000138532-5"},{"key":"ref51","first-page":"7167","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Lee","year":"2018"},{"key":"ref52","first-page":"9690","article-title":"Uncertainty estimation using a single deep deterministic neural network","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amersfoort","year":"2020"},{"issue":"42","key":"ref53","first-page":"1","article-title":"A simple approach to improve single-model deep uncertainty via distance-awareness","volume":"24","author":"Liu","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref54","first-page":"1","article-title":"Bayesian neural network priors revisited","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fortuin","year":"2022"},{"issue":"47","key":"ref55","first-page":"1","article-title":"On Markov chain monte carlo methods for tall data","volume":"18","author":"Bardenet","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/584091.584093"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1201\/b10905-6"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2638586"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00102"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2980004"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0919-5_26"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref64","first-page":"1352","article-title":"Radial Bayesian neural networks: Beyond discrete support in large-scale Bayesian deep learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Farquhar","year":"2020"},{"key":"ref65","first-page":"1303","article-title":"Stochastic variational inference","volume":"14","author":"Hoffman","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1561\/2200000001"},{"issue":"1","key":"ref67","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref68","first-page":"2782","article-title":"Efficient and scalable Bayesian neural nets with rank-1 factors","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dusenberry","year":"2020"},{"key":"ref69","first-page":"22686","article-title":"Tractable function-space variational inference in Bayesian neural networks","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"35","author":"Rudner","year":"2022"},{"key":"ref70","first-page":"1","article-title":"A scalable laplace approximation for neural networks","volume-title":"Proc. 6th Int. Conf. Learn. Representations Conf. Track Proc.","volume":"6","author":"Ritter","year":"2018"},{"key":"ref71","first-page":"13153","article-title":"A simple baseline for Bayesian uncertainty in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Maddox","year":"2019"},{"key":"ref72","first-page":"2611","article-title":"Fast and scalable Bayesian deep learning by weight-perturbation in adam","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Khan","year":"2018"},{"key":"ref73","first-page":"822","article-title":"Fast predictive uncertainty for classification with Bayesian deep networks","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Hobbhahn","year":"2022"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00157"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3086757"},{"key":"ref76","first-page":"1184","article-title":"Decomposition of uncertainty in Bayesian deep learning for efficient and risk-sensitive learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Depeweg","year":"2018"},{"key":"ref77","first-page":"2282","article-title":"Quantifying aleatoric and epistemic uncertainty in machine learning: Are conditional entropy and mutual information appropriate measures?","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Wimmer","year":"2023"},{"key":"ref78","first-page":"1","article-title":"Introducing an improved information-theoretic measure of predictive uncertainty","volume-title":"Proc. NeurIPS 2023 Workshop Math. Modern Mach. Learn.","author":"Schweighofer","year":"2023"},{"key":"ref79","first-page":"3159","article-title":"Label-wise aleatoric and epistemic uncertainty quantification","volume-title":"Proc. 14th Conf. Uncertainty Artif. Intell.","author":"Sale","year":"2024"},{"key":"ref80","first-page":"43060","article-title":"Second-order uncertainty quantification: A distance-based approach","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Sale","year":"2024"},{"key":"ref81","first-page":"3792","article-title":"Verified uncertainty calibration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar","year":"2019"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50146-4_41"},{"key":"ref83","first-page":"4629","article-title":"What are Bayesian neural network posteriors really like?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Izmailov","year":"2021"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2021.107875"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102914"},{"key":"ref86","first-page":"1","article-title":"Are Bayesian neural networks intrinsically good at out-of-distribution detection?","volume-title":"Proc. Workshop Uncertainty Robustness Deep Learn.","author":"Henning","year":"2021"},{"issue":"132","key":"ref87","first-page":"1","article-title":"An optimization-centric view on Bayes\u2019 rule: Reviewing and generalizing variational inference","volume":"23","author":"Knoblauch","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref88","first-page":"2021","article-title":"Benchmarking bayesian deep learning on diabetic retinopathy detection tasks","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Band"},{"key":"ref89","first-page":"8708","article-title":"NOMU: Neural optimization-based model uncertainty","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Heiss","year":"2022"},{"key":"ref90","first-page":"7694","article-title":"Do Bayesian neural networks need to be fully stochastic?","volume-title":"Proc. 26th Int. Conf. Artif. Intell. Statist.","volume":"206","author":"Sharma","year":"2023"},{"key":"ref91","first-page":"1","article-title":"Credal Bayesian deep learning","author":"Caprio","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-45528-0"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-019-09324-2"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59851-8_14"},{"key":"ref95","first-page":"1","article-title":"BatchEnsemble: An alternative approach to efficient ensemble and lifelong learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wen","year":"2020"},{"key":"ref96","first-page":"6514","article-title":"Hyperparameter ensembles for robustness and uncertainty quantification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wenzel","year":"2020"},{"key":"ref97","first-page":"18583","article-title":"Measuring robustness to natural distribution shifts in image classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Taori","year":"2020"},{"key":"ref98","first-page":"1","article-title":"Epistemic neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Osband","year":"2023"},{"key":"ref99","first-page":"7498","article-title":"Simple and principled uncertainty estimation with deterministic deep learning via distance awareness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Liu","year":"2020"},{"key":"ref100","first-page":"3451","article-title":"Repulsive deep ensembles are Bayesian","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"D\u2019Angelo","year":"2021"},{"key":"ref101","first-page":"1","article-title":"A rigorous link between deep ensembles and (variational) Bayesian methods","volume-title":"Proc. 37th Adv. Neural Inf. Process. Syst.","author":"Wild","year":"2023"},{"key":"ref102","article-title":"Deep ensembles: A loss landscape perspective","author":"Fort","year":"2019"},{"key":"ref103","first-page":"4697","article-title":"Bayesian deep learning and a probabilistic perspective of generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wilson","year":"2020"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177698950"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1515\/9780691214696"},{"key":"ref106","volume-title":"Subjective Logic: A Formalism for Reasoning Under Uncertainty.","author":"Jsang","year":"2018"},{"key":"ref107","article-title":"Introduction to the dirichlet distribution and related processes","author":"Frigyik","year":"2010"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1002\/0471722065"},{"key":"ref109","first-page":"1","article-title":"Ensemble distribution distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Malinin","year":"2019"},{"key":"ref110","first-page":"12851","article-title":"Uncertainty on asynchronous time event prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Bilo\u0161","year":"2019"},{"key":"ref111","first-page":"5707","article-title":"Evaluating robustness of predictive uncertainty estimation: Are dirichlet-based models reliable?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kopetzki","year":"2021"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6071"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190836"},{"key":"ref114","first-page":"17247","article-title":"Multifaceted uncertainty estimation for label-efficient deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Shi","year":"2020"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746756"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1111\/insr.12243"},{"key":"ref117","first-page":"3309","article-title":"Dangers of Bayesian model averaging under covariate shift","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Izmailov","year":"2021"},{"key":"ref118","first-page":"1","article-title":"Natural posterior network: Deep Bayesian predictive uncertainty for exponential family distributions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Charpentier","year":"2022"},{"key":"ref119","first-page":"2078","article-title":"On second-order scoring rules for epistemic uncertainty quantification","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Bengs","year":"2023"},{"key":"ref120","first-page":"22624","article-title":"Is epistemic uncertainty faithfully represented by evidential deep learning methods?","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Juergens","year":"2024"},{"key":"ref121","first-page":"107830","article-title":"Are uncertainty quantification capabilities of evidential deep learning a mirage?","volume-title":"Proc. 38th Adv. Neural Inf. Process. Syst.","author":"Shen","year":"2024"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20759"},{"key":"ref123","article-title":"Regression prior networks","author":"Malinin","year":"2020"},{"key":"ref124","article-title":"Multivariate deep evidential regression","author":"Meinert","year":"2021"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26096"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63153-6"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89197-0_12"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14049-5_73"},{"key":"ref129","first-page":"169","article-title":"Bayes\u2019 theorem generalized for belief functions","volume-title":"Proc. ECAI-86","volume":"2","author":"Smets","year":"1986"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijar.2022.06.007"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-17801-6_6"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(65)90241-X"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1023\/B:ISFI.0000005650.63806.03"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-75256-1_36"},{"key":"ref135","article-title":"CIFAR-10","author":"Krizhevsky","year":"2009"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref137","article-title":"Intel image classification: Image scene classification of multiclass","author":"Bansal","year":"2019"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref141","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref143","first-page":"6105","article-title":"EfficientNet:Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2019"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00064"},{"key":"ref145","volume-title":"The Enterprise of Knowledge: An Essay on Knowledge, Credal Probability, and Chance","author":"Levi","year":"1980"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-3758(01)00201-4"},{"issue":"4","key":"ref147","first-page":"581","article-title":"Learning reliable classifiers from small or incomplete data sets: The naive credal classifier 2","volume":"9","author":"Corani","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23166-7_4"},{"key":"ref149","first-page":"205","article-title":"Credal sum-product networks","volume-title":"Proc. 10th Int. Symp. Imprecise Probability, Theories Appl.","author":"Mau\u00e1","year":"2017"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref151","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"ref152","first-page":"1708","article-title":"Structured and efficient variational deep learning with matrix Gaussian posteriors","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Louizos","year":"2016"},{"key":"ref153","first-page":"1","article-title":"Deterministic variational inference for robust Bayesian neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2019"},{"key":"ref154","first-page":"1","article-title":"Variance networks: When expectation does not meet your expectations","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Neklyudov","year":"2019"},{"key":"ref155","first-page":"1744","article-title":"Structured variational learning of Bayesian neural networks with horseshoe priors","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ghosh","year":"2018"},{"issue":"4","key":"ref156","first-page":"5298","article-title":"Radial and directional posteriors for Bayesian neural networks","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"34","author":"Oh","year":"2020"},{"key":"ref157","article-title":"Interpretable outcome prediction with sparse Bayesian neural networks in intensive care","author":"Popkes","year":"2019"},{"key":"ref158","article-title":"Structured weight priors for convolutional neural networks","author":"Pearce","year":"2020"},{"key":"ref159","first-page":"8248","article-title":"Global inducing point variational posteriors for bayesian neural networks and deep Gaussian processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ober","year":"2021"},{"issue":"1","key":"ref160","first-page":"7045","article-title":"The ridgelet prior: A covariance function approach to prior specification for bayesian neural networks","volume":"22","author":"Matsubara","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref161","first-page":"134","article-title":"Expressive priors in Bayesian neural networks: Kernel combinations and periodic functions","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Pearce","year":"2020"},{"key":"ref162","first-page":"905","article-title":"Noise contrastive priors for functional uncertainty","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Hafner","year":"2020"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1142\/S0218488594000146"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2018.02.010"},{"key":"ref165","first-page":"728","article-title":"Fairness without demographics through adversarially reweighted learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lahoti","year":"2020"},{"key":"ref166","first-page":"20673","article-title":"Learning from failure: De-biasing classifier from biased classifier","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Nam","year":"2020"},{"key":"ref167","first-page":"1","article-title":"Distributionally robust neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sagawa","year":"2020"},{"key":"ref168","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"issue":"7","key":"ref169","article-title":"Tiny ImageNet visual recognition challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS 231 N"},{"key":"ref170","first-page":"1","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks","year":"2019"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02906-6_26"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.3150\/21-BEJ1447"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.734"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00971"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1080\/03081070500473490"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1142\/S0218488500000253"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1928.tb01236.x"},{"key":"ref179","first-page":"1","article-title":"Quantifying aleatoric and epistemic uncertainty: A credal approach","volume-title":"Proc. ICML 2024 Workshop Structured Probabilistic Inference Generative Model.","author":"Hofman","year":"2024"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.21236\/ADA459827"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.2307\/1913643"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2096824"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/101.17235"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1007\/11736790_1"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-015-2109-3"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1016\/0165-0114(93)90118-2"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2000.856123"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1016\/j.probengmech.2022.103370"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511526473"},{"key":"ref191","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1016\/S0008-8846(98)00165-3"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijar.2012.06.010"},{"key":"ref194","article-title":"Quality of uncertainty quantification for Bayesian neural network inference","author":"Yao","year":"2019"},{"key":"ref195","first-page":"2017","article-title":"A unified evaluation framework for epistemic predictions","volume-title":"Proc. 28th Int. Conf. Artif. Intell. Statist.","author":"Manchingal","year":"2025"},{"key":"ref196","first-page":"13956","article-title":"Url: A representation learning benchmark for transferable uncertainty estimates","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Kirchhof","year":"2023"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11372200\/11219221.pdf?arnumber=11219221","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:05:26Z","timestamp":1770671126000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11219221\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":196,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3626645","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}