Ribeiro, Fabio De SousaCalivá, FrancescoSwainson, MarkGudmundsson, KjartanLeontidis, GeorgiosKollias, Stefanos2020-06-102020-06-102020-05Ribeiro, F D S, Calivá, F, Swainson, M, Gudmundsson, K, Leontidis, G & Kollias, S 2020, 'Deep Bayesian Self-Training', Neural Computing and Applications, vol. 32, pp. 4275-4291. https://doi.org/10.1007/s00521-019-04332-40941-0643ORCID: /0000-0001-6671-5568/work/59336811https://hdl.handle.net/2164/14476Acknowledgements The authors would like to thank Mr. George Marandianos, Mrs. Mamatha Thota and Mr. Samuel Bond-Taylor for manually annotating datasets used in this study and of course the reviewers for their constructive feedback that helped to improve the manuscript. We would also like to thank Professor Luc Bidaut for enabling this collaboration. Funding The research presented in this paper was funded by Engineering and Physical Sciences Research Council (Reference Number EP/R005524/1) and Innovate UK (Reference Number 102908), in collaboration with the Olympus Automation Limited Company, for the project Automated Robotic Food Manufacturing System.171287179engMachine LearningDeep LearningDeep learningRepresentation learningBayesian CNNVariational inferenceClusteringSelf-trainingAdaptationUncertainty weightingQA75 Electronic computers. Computer scienceSoftwareArtificial IntelligenceEngineering and Physical Sciences Research Council (EPSRC)EP/R005524/1Innovate UK102908QA75Journal article10.1007/s00521-019-04332-4http://www.scopus.com/inward/record.url?scp=85069661389&partnerID=8YFLogxK32