{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:38:24Z","timestamp":1777657104862,"version":"3.51.4"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2019,7,10]],"date-time":"2019-07-10T00:00:00Z","timestamp":1562716800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,7,10]],"date-time":"2019-07-10T00:00:00Z","timestamp":1562716800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/R005524\/1"],"award-info":[{"award-number":["EP\/R005524\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006041","name":"Innovate UK","doi-asserted-by":"publisher","award":["102908"],"award-info":[{"award-number":["102908"]}],"id":[{"id":"10.13039\/501100006041","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1007\/s00521-019-04332-4","type":"journal-article","created":{"date-parts":[[2019,7,10]],"date-time":"2019-07-10T10:03:23Z","timestamp":1562753003000},"page":"4275-4291","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Deep Bayesian Self-Training"],"prefix":"10.1007","volume":"32","author":[{"given":"Fabio","family":"De Sousa Ribeiro","sequence":"first","affiliation":[]},{"given":"Francesco","family":"Caliv\u00e1","sequence":"additional","affiliation":[]},{"given":"Mark","family":"Swainson","sequence":"additional","affiliation":[]},{"given":"Kjartan","family":"Gudmundsson","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6671-5568","authenticated-orcid":false,"given":"Georgios","family":"Leontidis","sequence":"additional","affiliation":[]},{"given":"Stefanos","family":"Kollias","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,7,10]]},"reference":[{"key":"4332_CR1","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"key":"4332_CR2","unstructured":"Gal Y, Islam R, Ghahramani Z (2017) Deep Bayesian active learning with image data. arXiv preprint \narXiv:1703.02910"},{"issue":"3","key":"4332_CR3","first-page":"4","volume":"2","author":"X Zhu","year":"2006","unstructured":"Zhu X (2006) Semi-supervised learning literature survey. Comput Sci Univ Wis-Madison 2(3):4","journal-title":"Comput Sci Univ Wis-Madison"},{"key":"4332_CR4","doi-asserted-by":"crossref","unstructured":"Yarowsky D (1995) Unsupervised word sense disambiguation rivaling supervised methods. In: Proceedings of the 33rd annual meeting on Association for Computational Linguistics. Association for Computational Linguistics, pp 189\u2013196","DOI":"10.3115\/981658.981684"},{"key":"4332_CR5","unstructured":"Pratt LY (1993) Discriminability-based transfer between neural networks. In: Advances in neural information processing systems, pp 204\u2013211"},{"key":"4332_CR6","doi-asserted-by":"crossref","unstructured":"Blum A, Mitchell T (1998) Combining labeled and unlabeled data with co-training. In: Proceedings of the eleventh annual conference on Computational learning theory. ACM, pp 92\u2013100","DOI":"10.1145\/279943.279962"},{"key":"4332_CR7","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1613\/jair.295","volume":"4","author":"DA Cohn","year":"1996","unstructured":"Cohn DA, Ghahramani Z, Jordan MI (1996) Active learning with statistical models. J Artif Intell Res 4:129\u2013145","journal-title":"J Artif Intell Res"},{"key":"4332_CR8","doi-asserted-by":"publisher","first-page":"1529","DOI":"10.1109\/TKDE.2005.186","volume":"11","author":"Z-H Zhou","year":"2005","unstructured":"Zhou Z-H, Li M (2005) Tri-training: exploiting unlabeled data using three classifiers. IEEE Trans Knowl Data Eng 11:1529\u20131541","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"4332_CR9","volume-title":"Active learning: theory and applications","author":"T Simon","year":"2001","unstructured":"Simon T (2001) Active learning: theory and applications, vol 1. Stanford University, Stanford"},{"key":"4332_CR10","unstructured":"Han B, Yao Q, Yu X, Niu G, Xu M, Hu W, Tsang I, Sugiyama M (2018) Co-teaching: robust training of deep neural networks with extremely noisy labels. In: Advances in neural information processing systems, pp 8527\u20138537"},{"key":"4332_CR11","unstructured":"Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? In: Advances in neural information processing systems, pp 3320\u20133328"},{"key":"4332_CR12","doi-asserted-by":"crossref","unstructured":"Zamir AR, Sax A, Shen W, Guibas L, Malik J, Savarese S (2018) Taskonomy: Disentangling task transfer learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3712\u20133722","DOI":"10.1109\/CVPR.2018.00391"},{"key":"4332_CR13","doi-asserted-by":"crossref","unstructured":"Sousa Ribeiro FD, Caliv\u00e1 F, Swainson M, Gudmundsson K, Leontidis G, Kollias S (2018) An adaptable deep learning system for optical character verification in retail food packaging. In: IEEE international conference on evolving and adaptive intelligent systems","DOI":"10.1109\/EAIS.2018.8397178"},{"key":"4332_CR14","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.gfs.2019.02.002","volume":"20","author":"S Pearson","year":"2019","unstructured":"Pearson S, May D, Leontidis G, Swainson M, Brewer S, Bidaut L, Frey JG, Parr G, Maull R (2019) Zisman A (2019) Are distributed ledger technologies the panacea for food traceability? Glob Food Secur 20:145\u2013149","journal-title":"Glob Food Secur"},{"key":"4332_CR15","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der\u00a0Maaten Laurens, Weinberger KQ (2017) Densely connected convolutional networks. In: CVPR, vol 1, p 3","DOI":"10.1109\/CVPR.2017.243"},{"key":"4332_CR16","doi-asserted-by":"crossref","unstructured":"Sousa Ribeiro FD, Gong L, Caliv\u00e1 F, Swainson M, Gudmundsson K, Yu M, Leontidis G, Ye X, Kollias S (2018) An end-to-end deep neural architecture for optical character verification and recognition in retail food packaging. In: 2018 25th IEEE international conference on image processing (ICIP). IEEE, pp 2376\u20132380","DOI":"10.1109\/ICIP.2018.8451555"},{"key":"4332_CR17","doi-asserted-by":"crossref","unstructured":"Sun C, Shrivastava A, Singh S, Gupta A (2017) Revisiting unreasonable effectiveness of data in deep learning era. In: 2017 IEEE international conference on computer vision (ICCV). IEEE, pp 843\u2013852","DOI":"10.1109\/ICCV.2017.97"},{"key":"4332_CR18","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.cmpb.2018.02.016","volume":"158","author":"P Chudzik","year":"2018","unstructured":"Chudzik P, Majumdar S, Caliv\u00e1 F, Al-Diri B, Hunter A (2018) Microaneurysm detection using fully convolutional neural networks. Comput Methods Programs Biomed 158:185\u2013192","journal-title":"Comput Methods Programs Biomed"},{"key":"4332_CR19","doi-asserted-by":"crossref","unstructured":"Kollias D, Yu M, Tagaris A, Leontidis G, Stafylopatis A, Kollias S (2017) Adaptation and contextualization of deep neural network models. In: 2017 IEEE symposium series on computational intelligence (SSCI), pp 1\u20138","DOI":"10.1109\/SSCI.2017.8280975"},{"key":"4332_CR20","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.media.2016.05.004","volume":"35","author":"M Havaei","year":"2017","unstructured":"Havaei M, Davy A, Warde-Farley D, Biard A, Courville A, Bengio Y, Pal C, Jodoin P-M, Larochelle H (2017) Brain tumor segmentation with deep neural networks. Med Image Anal 35:18\u201331","journal-title":"Med Image Anal"},{"key":"4332_CR21","doi-asserted-by":"crossref","unstructured":"Caliva F, Sousa Ribeiro FD, Mylonakis A, Demaziere C, Vinai P, Leontidis G, Kollias S (2018) A deep learning approach to anomaly detection in nuclear reactors. In: 2018 International joint conference on neural networks (IJCNN), pp 1\u20138","DOI":"10.1109\/IJCNN.2018.8489130"},{"key":"4332_CR22","unstructured":"Sousa Ribeiro FD, Caliva F, Chionis D, Dokhane A, Mylonakis A, Demaziere C, Leontidis G, Kollias S (2018) Towards a deep unified framework for nuclear reactor perturbation analysis. In: 2018 IEEE symposium series on computational intelligence (SSCI), pp 1\u20138"},{"key":"4332_CR23","unstructured":"Kaiser L, Gomez AN., Shazeer N, Vaswani A, Parmar N, Jones L, Uszkoreit J (2017) One model to learn them all. arXiv preprint \narXiv:1706.05137"},{"key":"4332_CR24","doi-asserted-by":"crossref","unstructured":"Doersch C, Zisserman A (2017) Multi-task self-supervised visual learning. In: The IEEE international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2017.226"},{"key":"4332_CR25","unstructured":"Zoph B, Vijay V, Shlens J, Le QV (2017) Learning transferable architectures for scalable image recognition. 2(6). arXiv preprint \narXiv:1707.07012"},{"key":"4332_CR26","unstructured":"Kingma DP, Mohamed S, Rezende DJ, Welling M (2014) Semi-supervised learning with deep generative models. In: Advances in neural information processing systems, pp 3581\u20133589"},{"key":"4332_CR27","doi-asserted-by":"crossref","unstructured":"Tzeng E, Hoffman J, Saenko K, Darrell T (2017) Adversarial discriminative domain adaptation. In: Computer vision and pattern recognition (CVPR), vol 1, no 4. pp 7167\u20137176","DOI":"10.1109\/CVPR.2017.316"},{"key":"4332_CR28","doi-asserted-by":"crossref","unstructured":"Bousmalis K, Silberman N, Dohan D, Erhan D, Krishnan D (2017) Unsupervised pixel-level domain adaptation with generative adversarial networks. In: The IEEE conference on computer vision and pattern recognition (CVPR), vol 1, no 7","DOI":"10.1109\/CVPR.2017.18"},{"key":"4332_CR29","unstructured":"Tarvainen A, Valpola H(2017) Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in neural information processing systems, pp 1195\u20131204"},{"key":"4332_CR30","doi-asserted-by":"crossref","unstructured":"Qiao S, Shen W, Zhang Z, Wang B, Yuille A (2018) Deep co-training for semi-supervised image recognition. In: Proceedings of the European conference on computer vision (ECCV) pp 135\u2013152","DOI":"10.1007\/978-3-030-01267-0_9"},{"key":"4332_CR31","unstructured":"Lee D-H (2013) Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on challenges in representation learning, ICML, vol 3, pp 2"},{"key":"4332_CR32","unstructured":"Grandvalet Y, Bengio Y (2005) Semi-supervised learning by entropy minimization. In: Advances in neural information processing systems, pp 529\u2013536"},{"key":"4332_CR33","doi-asserted-by":"crossref","unstructured":"Zou Y, Yu Z, Vijaya Kumar BVK, Wang J (2018) Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: Proceedings of the European conference on computer vision (ECCV), pp 289\u2013305","DOI":"10.1007\/978-3-030-01219-9_18"},{"key":"4332_CR34","unstructured":"Kendall A, Gal Y (2017) What uncertainties do we need in Bayesian deep learning for computer vision? In: Advances in neural information processing systems, pp 5574\u20135584"},{"key":"4332_CR35","unstructured":"Denker JS, Lecun Y (1991) Transforming neural-net output levels to probability distributions. In: Advances in neural information processing systems, pp 853\u2013859"},{"key":"4332_CR36","volume-title":"Bayesian learning for neural networks","author":"RM Neal","year":"2012","unstructured":"Neal RM (2012) Bayesian learning for neural networks, vol 118. Springer, New York"},{"issue":"3","key":"4332_CR37","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1162\/neco.1992.4.3.448","volume":"4","author":"DJC MacKay","year":"1992","unstructured":"MacKay DJC (1992) A practical bayesian framework for backpropagation networks. Neural Comput 4(3):448\u2013472","journal-title":"Neural Comput"},{"key":"4332_CR38","volume-title":"Uncertainty in deep learning","author":"G Yarin","year":"2016","unstructured":"Yarin G (2016) Uncertainty in deep learning. University of Cambridge, Cambridge"},{"key":"4332_CR39","unstructured":"Gal Y, Ghahramani Z (2015) Bayesian convolutional neural networks with Bernoulli approximate variational inference. arXiv preprint \narXiv:1506.02158"},{"key":"4332_CR40","unstructured":"Kendall A, Gal Y, Cipolla R (2017) Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. arXiv preprint \narXiv:1705.07115"},{"key":"4332_CR41","unstructured":"Gal Y, Ghahramani Z (2016) Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: international conference on machine learning, pp 1050\u20131059"},{"key":"4332_CR42","unstructured":"Hinton GE, Van Camp D (1993) Keeping the neural networks simple by minimizing the description length of the weights. In: Proceedings of the sixth annual conference on Computational learning theory, ACM, pp 5\u201313"},{"key":"4332_CR43","unstructured":"Graves A (2011) Practical variational inference for neural networks. In: Advances in neural information processing systems, pp 2348\u20132356"},{"key":"4332_CR44","unstructured":"Welling M, Teh YW (2011) Bayesian learning via stochastic gradient Langevin dynamics. In: Proceedings of the 28th international conference on machine learning (ICML-11), pp 681\u2013688"},{"key":"4332_CR45","unstructured":"Kingma DP, Welling M (2013) Auto-encoding variational Bayes. arXiv preprint \narXiv:1312.6114"},{"key":"4332_CR46","unstructured":"Maddison CJ, Mnih A, Teh YW (2016) The concrete distribution: a continuous relaxation of discrete random variables. arXiv preprint \narXiv:1611.00712"},{"key":"4332_CR47","unstructured":"Gal Y, Hron J, Kendall A (2017) Concrete dropout. In: Advances in neural information processing systems, pp 3581\u20133590"},{"key":"4332_CR48","unstructured":"Pereyra G, Tucker G, Chorowski J, Kaiser \u0141, Hinton G (2017) Regularizing neural networks by penalizing confident output distributions. arXiv preprint \narXiv:1701.06548"},{"key":"4332_CR49","unstructured":"Kwon Y, Won J-H, Kim BJ, Paik MC (2018) Uncertainty quantification using Bayesian neural networks in classification: application to ischemic stroke lesion segmentation. In: International conference on medical imaging with deep learning"},{"key":"4332_CR50","unstructured":"Arthur D, Vassilvitskii S (2007) k-means++: the advantages of careful seeding. In: Proceedings of the eighteenth annual ACM-SIAM symposium on discrete algorithms. Society for Industrial and Applied Mathematics, pp 1027\u20131035"},{"key":"4332_CR51","doi-asserted-by":"crossref","unstructured":"J\u00e9gou S, Drozdzal M, Vazquez D, Romero A, Bengio Y (2017) The one hundred layers tiramisu: fully convolutional densenets for semantic segmentation. In: 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW). IEEE, pp 1175\u20131183","DOI":"10.1109\/CVPRW.2017.156"},{"key":"4332_CR52","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint \narXiv:1502.03167"},{"key":"4332_CR53","unstructured":"Lakshminarayanan B, Pritzel A, Blundell C (2017) Simple and scalable predictive uncertainty estimation using deep ensembles. In: Advances in neural information processing systems, pp 6402\u20136413"},{"key":"4332_CR54","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"issue":"1","key":"4332_CR55","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"4332_CR56","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint \narXiv:1412.6980"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-019-04332-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00521-019-04332-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-019-04332-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,8]],"date-time":"2020-07-08T23:23:31Z","timestamp":1594250611000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00521-019-04332-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,10]]},"references-count":56,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2020,5]]}},"alternative-id":["4332"],"URL":"https:\/\/doi.org\/10.1007\/s00521-019-04332-4","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,10]]},"assertion":[{"value":"3 November 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}