{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:19:32Z","timestamp":1778084372133,"version":"3.51.4"},"reference-count":200,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Central South University Post-Graduate Independent Exploration and Innovation Project","award":["2025ZZTS0616"],"award-info":[{"award-number":["2025ZZTS0616"]}]},{"name":"National Major Scientific Research Equipment of China","award":["61927803"],"award-info":[{"award-number":["61927803"]}]},{"DOI":"10.13039\/501100020771","name":"Natural Science Foundation for Young Scientists of Shanxi Province","doi-asserted-by":"publisher","award":["62303491"],"award-info":[{"award-number":["62303491"]}],"id":[{"id":"10.13039\/501100020771","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Program of Xiangjiang Laboratory","award":["22XJ01005"],"award-info":[{"award-number":["22XJ01005"]}]},{"DOI":"10.13039\/501100001809","name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61621062"],"award-info":[{"award-number":["61621062"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tnnls.2025.3565159","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T13:39:38Z","timestamp":1750253978000},"page":"15664-15684","source":"Crossref","is-referenced-by-count":5,"title":["A Survey on Confidence Calibration of Deep Learning-Based Classification Models Under Class Imbalance Data"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9742-0295","authenticated-orcid":false,"given":"Jinzong","family":"Dong","sequence":"first","affiliation":[{"name":"School of Automation, Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4861-5819","authenticated-orcid":false,"given":"Zhaohui","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Automation, Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1876-3108","authenticated-orcid":false,"given":"Dong","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Automation, Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4759-0904","authenticated-orcid":false,"given":"Zhiwen","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Automation, Central South University, Changsha, China"}]},{"given":"Qingyi","family":"Guan","sequence":"additional","affiliation":[{"name":"School of Automation, Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9953-391X","authenticated-orcid":false,"given":"Hongbin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Automation, Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8576-0831","authenticated-orcid":false,"given":"Gui","family":"Gui","sequence":"additional","affiliation":[{"name":"School of Automation, Central South University, Changsha, China"}]},{"given":"Weihua","family":"Gui","sequence":"additional","affiliation":[{"name":"School of Automation, Central South University, Changsha, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3360002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.105849"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3422214"},{"key":"ref4","first-page":"15288","article-title":"Cal-DETR: Calibrated detection transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Munir"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2011-000291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3008150"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110385","article-title":"BALQUE: Batch active learning by querying unstable examples with calibrated confidence","volume":"151","author":"Han","year":"2024","journal-title":"Pattern Recognit."},{"key":"ref8","doi-asserted-by":"crossref","first-page":"6316","DOI":"10.18653\/v1\/2023.findings-acl.393","article-title":"Distilling calibrated knowledge for stance detection","volume-title":"Findings of the Association for Computational Linguistics: ACL 2023","author":"Li","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3353762"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238024"},{"key":"ref11","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref12","first-page":"6577","article-title":"A survey of confidence estimation and calibration in large language models","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Geng"},{"issue":"15","key":"ref13","first-page":"16317","article-title":"Combining priors with experience: Confidence calibration based on binomial process modeling","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"39","author":"Dong"},{"key":"ref14","first-page":"68511","article-title":"Proximity-informed calibration for deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Xiong"},{"key":"ref15","first-page":"60329","article-title":"Enhancing minority classes by mixing: An adaptative optimal transport approach for long-tailed classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Gao"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29262"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2024.102513","article-title":"Faulty rolling bearing digital twin model and its application in fault diagnosis with imbalanced samples","volume":"61","author":"Qin","year":"2024","journal-title":"Adv. Eng. Informat."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0192-5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02269"},{"key":"ref20","first-page":"1","article-title":"LPT: Long-tailed prompt tuning for image classification","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Dong"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3047335"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01913"},{"key":"ref23","first-page":"2529","article-title":"On model calibration for long-tailed object detection and instance segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan"},{"key":"ref24","first-page":"7139","article-title":"Towards calibrated model for long-tailed visual recognition from prior perspective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref25","first-page":"1","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01622"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10562-9"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06336-7"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3716317"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.05.037"},{"issue":"4","key":"ref31","first-page":"42","article-title":"An overview of classification algorithms for imbalanced datasets","volume":"2","author":"Ganganwar","year":"2012","journal-title":"Int. J. Emerg. Technol. Adv. Eng."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3268118"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.08.031"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3539314"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3531662"},{"key":"ref36","article-title":"A comparative study of confidence calibration in deep learning: From computer vision to medical imaging","author":"Gao","year":"2022","journal-title":"arXiv:2206.08833"},{"issue":"3","key":"ref37","first-page":"61","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","volume":"10","author":"Platt","year":"1999","journal-title":"Adv. Large Margin Classifiers"},{"key":"ref38","first-page":"609","article-title":"Obtaining calibrated probability estimates from decision trees and Naive Bayesian classifiers","volume-title":"Proc. 18th Int. Conf. Mach. Learn.","author":"Zadrozny"},{"key":"ref39","first-page":"1","article-title":"Evidential deep learning to quantify classification uncertainty","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Sensoy"},{"issue":"42","key":"ref40","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":"ref41","doi-asserted-by":"publisher","DOI":"10.1111\/insr.12502"},{"key":"ref42","first-page":"1613","article-title":"Weight uncertainty in neural network","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blundell"},{"key":"ref43","article-title":"Top-label calibration and multiclass-to-binary reductions","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gupta"},{"key":"ref44","first-page":"1","article-title":"Beyond temperature scaling: Obtaining well-calibrated multi-class probabilities with Dirichlet calibration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kull"},{"key":"ref45","first-page":"3459","article-title":"Evaluating model calibration in classification","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"Vaicenavicius"},{"key":"ref46","article-title":"Calibration of neural networks using splines","author":"Gupta","year":"2020","journal-title":"arXiv:2006.12800"},{"key":"ref47","first-page":"1","article-title":"LaSCal: Label-shift calibration without target labels","volume-title":"Proc. 38th Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Popordanoska"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01542"},{"key":"ref49","first-page":"4694","article-title":"When does label smoothing help","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"M\u00fcller"},{"key":"ref50","first-page":"1","article-title":"Your classifier is secretly an energy based model and you should treat it like one","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Grathwohl"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00643"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01510"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3358113"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9602"},{"key":"ref55","first-page":"14919","article-title":"Sample-dependent adaptive temperature scaling for improved calibration","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Joy"},{"key":"ref56","first-page":"11117","article-title":"Mix-n-match: Ensemble and compositional methods for uncertainty calibration in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zhang"},{"key":"ref57","first-page":"1","article-title":"Multi-class uncertainty calibration via mutual information maximization-based binning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Patel"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775151"},{"key":"ref59","first-page":"13456","article-title":"Intra order-preserving functions for calibration of multi-class neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rahimi"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00786"},{"key":"ref61","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Cao"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096769"},{"key":"ref64","article-title":"Class-distribution-aware calibration for long-tailed visual recognition","author":"Islam","year":"2021","journal-title":"arXiv:2109.05263"},{"key":"ref65","first-page":"2712","article-title":"Using pre-training can improve model robustness and uncertainty","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Hendrycks"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1080\/23270012.2022.2031324"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00976"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3384961"},{"key":"ref69","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.123987","article-title":"IMWMOTE: A novel oversampling technique for fault diagnosis in heterogeneous imbalanced data","volume":"251","author":"Wang","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3373668"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ComPE49325.2020.9200087"},{"key":"ref72","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.neucom.2021.01.033","article-title":"Relevant information undersampling to support imbalanced data classification","volume":"436","author":"Hoyos-Osorio","year":"2021","journal-title":"Neurocomputing"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3136503"},{"key":"ref74","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108511","article-title":"FW-SMOTE: A feature-weighted oversampling approach for imbalanced classification","volume":"124","author":"Maldonado","year":"2022","journal-title":"Pattern Recognit."},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10186-5"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533415"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA51439.2020.9264517"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s00607-020-00854-1"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2015.33"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/s10472-024-09952-8"},{"key":"ref81","first-page":"101","article-title":"Density-aware personalized training for risk prediction in imbalanced medical data","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Huo"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88942-5_19"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3364500"},{"key":"ref84","first-page":"1112","article-title":"A rationale-centric counterfactual data augmentation method for cross-document event coreference resolution","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Ding"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref86","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109608","article-title":"Margin-aware rectified augmentation for long-tailed recognition","volume":"141","author":"Xiang","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_26"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-65414-6_9"},{"key":"ref89","first-page":"20551","article-title":"Data augmentation for compositional data: Advancing predictive models of the microbiome","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gordon-Rodriguez"},{"key":"ref90","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref91","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1982.tb01195.x"},{"key":"ref93","first-page":"6680","article-title":"Representation learning of compositional data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Avalos-Fernandez"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3185008"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3366991"},{"issue":"18","key":"ref97","doi-asserted-by":"crossref","first-page":"9007","DOI":"10.3390\/app12189007","article-title":"A study on the calibrated confidence of text classification using a variational Bayes","volume":"12","author":"Lee","year":"2022","journal-title":"Appl. Sci."},{"key":"ref98","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Sohn"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.5220\/0006576003790386"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3385656"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.12.017"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAS56421.2023.10082744"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1175\/2009MWR2715.1"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00684"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43898-1_11"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328829"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01912"},{"key":"ref108","first-page":"16596","article-title":"Neural bootstrapper","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shin"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_15"},{"key":"ref110","article-title":"Long-tailed recognition by routing diverse distribution-aware experts","author":"Wang","year":"2020","journal-title":"arXiv:2010.01809"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45014-9_1"},{"key":"ref112","article-title":"Deep ensembles: A loss landscape perspective","author":"Fort","year":"2019","journal-title":"arXiv:1912.02757"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.4018\/9781599048499.ch068"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-44792-4_3"},{"key":"ref115","article-title":"Long-tail learning via logit adjustment","author":"Krishna Menon","year":"2020","journal-title":"arXiv:2007.07314"},{"key":"ref116","article-title":"Generative multiple-purpose sampler for weighted M-estimation","author":"Shin","year":"2020","journal-title":"arXiv:2006.00767"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00446"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599525"},{"key":"ref119","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1007\/978-3-031-54605-1_38","article-title":"Multiclass alignment of confidence and certainty for network calibration, \"Multiclass alignment of confidence and certainty for network calibration","volume-title":"Pattern Recognition","author":"Kugathasan","year":"2024"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00656"},{"key":"ref121","first-page":"23429","article-title":"Calibrating multimodal learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534411"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01561"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00751"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26284-5_17"},{"key":"ref126","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01516"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00678"},{"key":"ref129","first-page":"4175","article-title":"Balanced meta-softmax for long-tailed visual recognition","volume-title":"Proc. NIPS","author":"Ren"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-4752-2_65"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01831-9"},{"key":"ref132","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.126276","article-title":"Dynamic prior probability network for long-tailed visual recognition","volume":"268","author":"Zhou","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00094"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-022-00735-3"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref136","first-page":"145","article-title":"Calibrating imbalanced classifiers with focal loss: An empirical study","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process., Ind. Track","author":"Wang"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3197937"},{"key":"ref138","first-page":"7047","article-title":"Predictive uncertainty estimation via prior networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Malinin"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21314"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.59"},{"key":"ref141","article-title":"On the role of dataset quality and heterogeneity in model confidence","author":"Zhao","year":"2020","journal-title":"arXiv:2002.09831"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16449-1_66"},{"key":"ref143","article-title":"Dual-branch temperature scaling calibration for long-tailed recognition","author":"Guo","year":"2023","journal-title":"arXiv:2308.08366"},{"key":"ref144","doi-asserted-by":"crossref","DOI":"10.21428\/594757db.da1a3d44","article-title":"Class-wise calibration: A case study on COVID-19 hate speech","volume-title":"Proc. Can. AI","author":"Obadinma"},{"key":"ref145","article-title":"Scaling of class-wise training losses for post-hoc calibration","author":"Jung","year":"2023","journal-title":"arXiv:2306.10989"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20326"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36718-3_36"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2023.107214"},{"key":"ref149","first-page":"8101","article-title":"Posterior re-calibration for imbalanced datasets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tian"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.3150\/21-BEJ1447"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5355-6"},{"key":"ref152","first-page":"16462","article-title":"Stable conformal prediction sets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ndiaye"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-41142-7_43"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.7b00159"},{"key":"ref155","article-title":"Mondrian confidence machine","author":"Vovk","year":"2003"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-75762-5_46"},{"key":"ref157","first-page":"94","article-title":"Bayes at FigLang 2022 euphemism detection shared task: Cost-sensitive Bayesian fine-tuning and venn-abers predictors for robust training under class skewed distributions","volume-title":"Proc. 3rd Workshop Figurative Lang. Process. (FLP)","author":"Trust"},{"key":"ref158","article-title":"Venn-abers predictors","author":"Vovk","year":"2012","journal-title":"arXiv:1211.0025"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-016-0578-3"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3425148"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3379929"},{"key":"ref162","article-title":"Representation norm amplification for out-of-distribution detection in long-tail learning","author":"Shin","year":"2024","journal-title":"arXiv:2408.10676"},{"key":"ref163","first-page":"1","article-title":"Confidence-calibrated clinical decision support system for reliable respiratory disease screening","volume-title":"Proc. IEEE EMBS Int. Conf. Biomed. Health Informat. (BHI)","author":"Nnamdi"},{"key":"ref164","first-page":"38420","article-title":"Beyond confidence: Reliable models should also consider atypicality","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Y\u00fcksekg\u00f6n\u00fcl"},{"key":"ref165","first-page":"184","article-title":"Adapting deep features for scene recognition utilizing places database","volume-title":"Proc. 2nd Int. Conf. Inventive Commun. Comput. Technol. (ICICCT)","author":"Raturi"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref168","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2012.115"},{"key":"ref170","first-page":"3466","article-title":"Consistent and asymptotically unbiased estimation of proper calibration errors","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Popordanoska"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1214\/20-aos1965"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2767540"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2024.110657"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2021.02.042"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2023.3272317"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3342285"},{"key":"ref177","doi-asserted-by":"crossref","first-page":"1600","DOI":"10.1016\/j.ins.2022.06.076","article-title":"A novel severity calibration algorithm for defect detection by constructing maps","volume":"607","author":"Li","year":"2022","journal-title":"Inf. Sci."},{"key":"ref178","doi-asserted-by":"crossref","DOI":"10.1016\/j.measurement.2023.113708","article-title":"An efficient defect detection method for nuclear-fuel rod grooves through weakly supervised learning","volume":"222","author":"Li","year":"2023","journal-title":"Measurement"},{"key":"ref179","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2024.102717","article-title":"Defect detection on multi-type rail surfaces via IoU decoupling and multi-information alignment","volume":"62","author":"Ni","year":"2024","journal-title":"Adv. Eng. Informat."},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2021.3059860"},{"key":"ref181","doi-asserted-by":"crossref","DOI":"10.1016\/j.compind.2024.104187","article-title":"Automated corner grading of trading cards: Defect identification and confidence calibration through deep learning","volume":"164","author":"Nahar","year":"2025","journal-title":"Comput. Ind."},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-022-00624-0"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-17419-7"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107816"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104527"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10884-2"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3286484"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-022-00573-8"},{"key":"ref189","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.engappai.2018.07.008","article-title":"How artificial intelligence and machine learning research impacts payment card fraud detection: A survey and industry benchmark","volume":"76","author":"Ryman-Tubb","year":"2018","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref190","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106248","article-title":"Uncertainty-aware credit card fraud detection using deep learning","volume":"123","author":"Habibpour","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref191","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.114750","article-title":"A hybrid method with dynamic weighted entropy for handling the problem of class imbalance with overlap in credit card fraud detection","volume":"175","author":"Li","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3502442"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1145\/2542048"},{"key":"ref194","article-title":"Confidence calibration for recommender systems and its applications","author":"Kweon","year":"2024","journal-title":"arXiv:2402.16325"},{"key":"ref195","first-page":"7246","article-title":"RECAL: Sample-relation guided confidence calibration over tabular data","volume-title":"Proc. Findings Assoc. Comput. Linguistics: EMNLP","author":"HaoTian"},{"key":"ref196","first-page":"4036","article-title":"Mitigating bias in calibration error estimation","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Roelofs"},{"key":"ref197","first-page":"7933","article-title":"A consistent and differentiable lp canonical calibration error estimator","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Popordanoska"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11151745\/11038829.pdf?arnumber=11038829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T17:46:52Z","timestamp":1757353612000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11038829\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":200,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3565159","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.171623912.22862601\/v2","asserted-by":"object"}]},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}