{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T03:38:00Z","timestamp":1774064280008,"version":"3.50.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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 Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3552157","type":"journal-article","created":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T17:42:42Z","timestamp":1742233362000},"page":"48502-48519","source":"Crossref","is-referenced-by-count":1,"title":["Runtime Verification for Visual Deep Learning Systems With Loss Prediction"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9685-9906","authenticated-orcid":false,"given":"Birk","family":"Torpmann-Hagen","sequence":"first","affiliation":[{"name":"Institute for Computer Science, UiT The Arctic University of Tromsø, Tromsø, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3153-2064","authenticated-orcid":false,"given":"Michael A.","family":"Riegler","sequence":"additional","affiliation":[{"name":"Department of Holistic Systems, SimulaMet, Oslo, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2073-7029","authenticated-orcid":false,"given":"P\u00e5l","family":"Halvorsen","sequence":"additional","affiliation":[{"name":"Department of Holistic Systems, SimulaMet, Oslo, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7067-6477","authenticated-orcid":false,"given":"Dag","family":"Johansen","sequence":"additional","affiliation":[{"name":"Institute for Computer Science, UiT The Arctic University of Tromsø, Tromsø, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The clever Hans effect in anomaly detection","author":"Kauffmann","year":"2020","journal-title":"arXiv:2006.10609"},{"key":"ref2","article-title":"Underspecification presents challenges for credibility in modern machine learning","author":"D\u2019Amour","year":"2020","journal-title":"arXiv:2011.03395"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3368555.3384468"},{"key":"ref5","article-title":"Assessing generalisability of deep learning-based polyp detection and segmentation methods through a computer vision challenge","author":"Ali","year":"2022","journal-title":"arXiv:2202.12031"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2019.00025"},{"key":"ref7","article-title":"Concrete problems in AI safety","author":"Amodei","year":"2016","journal-title":"arXiv:1606.06565"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.083"},{"key":"ref9","article-title":"OoD-bench: Quantifying and understanding two dimensions of out-of-distribution generalization","author":"Ye","year":"2021","journal-title":"arXiv:2106.03721"},{"key":"ref10","article-title":"Towards out-of-distribution generalization: A survey","author":"Liu","year":"2021","journal-title":"arXiv:2108.13624"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","article-title":"A review of uncertainty quantification in deep learning: Techniques, applications and challenges","volume":"76","author":"Abdar","year":"2021","journal-title":"Inf. Fusion"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02117-4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00013"},{"key":"ref14","article-title":"On the importance of gradients for detecting distributional shifts in the wild","author":"Huang","year":"2021","journal-title":"arXiv:2110.00218"},{"key":"ref15","article-title":"How useful are gradients for OOD detection really?","author":"Igoe","year":"2022","journal-title":"arXiv:2205.10439"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190679"},{"key":"ref17","article-title":"On pitfalls in ood detection: Entropy considered harmful","volume-title":"Proc. Uncertainty Robustness Deep Learn. Workshop (ICML)","author":"Kirsch"},{"key":"ref18","volume-title":"Statistical Learning Theory","author":"Vapnik","year":"1998"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1037\/\/0033-295x.102.3.419"},{"issue":"3","key":"ref21","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1055\/a-1201-7165","article-title":"Artificial intelligence for polyp detection during colonoscopy: A systematic review and meta-analysis","volume":"53","author":"Barua","year":"2021","journal-title":"Endoscopy"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1186\/s11782-020-00082-6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-bioeng-071516-044442"},{"key":"ref24","article-title":"A survey of the usages of deep learning in natural language processing","author":"Otter","year":"2018","journal-title":"arXiv:1807.10854"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2017.1365009"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09744-1"},{"issue":"7587","key":"ref27","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1001\/jamadermatol.2019.1735"},{"key":"ref29","article-title":"Adversarial examples are not bugs, they are features","author":"Ilyas","year":"2019","journal-title":"arXiv:1905.02175"},{"key":"ref30","article-title":"Do ImageNet classifiers generalize to ImageNet?","author":"Recht","year":"2019","journal-title":"arXiv:1902.10811"},{"key":"ref31","article-title":"Do CIFAR-10 classifiers generalize to CIFAR-10?","author":"Recht","year":"2018","journal-title":"arXiv:1806.00451"},{"key":"ref32","article-title":"The reversal curse: LLMs trained on \u2019A is B\u2019 fail to learn \u2019B is A","author":"Berglund","year":"2023","journal-title":"arXiv:2309.12288"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.213"},{"key":"ref34","article-title":"Formalizing trust in artificial intelligence: Prerequisites, causes and goals of human trust in AI","author":"Jacovi","year":"2020","journal-title":"arXiv:2010.07487"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1016\/j.infsof.2020.106368","article-title":"Large-scale machine learning systems in real-world industrial settings: A review of challenges and solutions","volume":"127","author":"Lwakatare","year":"2020","journal-title":"Inf. Softw. Technol."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300830"},{"key":"ref37","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"issue":"1","key":"ref38","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1016\/j.patcog.2011.06.019","article-title":"A unifying view on dataset shift in classification","volume":"45","author":"Moreno-Torres","year":"2012","journal-title":"Pattern Recognit."},{"key":"ref39","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"Hendrycks","year":"2016","journal-title":"arXiv:1610.02136"},{"key":"ref40","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","author":"Liang","year":"2017","journal-title":"arXiv:1706.02690"},{"key":"ref41","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Liu"},{"key":"ref42","article-title":"Generalization guarantees for neural networks via harnessing the low-rank structure of the Jacobian","author":"Oymak","year":"2019","journal-title":"arXiv:1906.05392"},{"key":"ref43","article-title":"Failing loudly: An empirical study of methods for detecting dataset shift","author":"Rabanser","year":"2018","journal-title":"arXiv:1810.11953"},{"key":"ref44","first-page":"20827","article-title":"Out-of-distribution detection with deep nearest neighbors","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2496947"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-040522-115238"},{"key":"ref47","article-title":"Detecting Out-of-Distribution inputs to deep generative models using typicality","author":"Nalisnick","year":"2019","journal-title":"arXiv:1906.02994"},{"key":"ref48","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"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3393296"},{"key":"ref50","volume-title":"PyTorch Lightning","author":"Falcon","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/info11020125"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37734-2_37"},{"key":"ref53","article-title":"Assessing generalisability of deep learning-based polyp detection and segmentation methods through a computer vision challenge","volume-title":"Proc. 2nd Int. Workshop Challenge Comput. Vis. Endoscopy (EndoCV)","volume":"2595","author":"Ali"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-013-0926-3"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40994-3_25"},{"key":"ref56","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"arXiv:1512.03385"},{"key":"ref57","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv:1706.05587"},{"key":"ref58","first-page":"10215","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Kingma"},{"key":"ref59","article-title":"Model-agnostic out-of-distribution detection using combined statistical tests","author":"Bergamin","year":"2022","journal-title":"arXiv:2203.01097"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3510457.3513036"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-020-09881-0"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10930478.pdf?arnumber=10930478","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T18:43:26Z","timestamp":1742841806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10930478\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3552157","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}