{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-bayesian-active-semi-supervised-learning","title":"Deep Bayesian Active Semi-Supervised Learning","arxiv_id":"1803.01216","date":"2018-03-03","proceeding":null,"authors":["Matthias Rottmann","Karsten Kahl","Hanno Gottschalk"],"abstract":"In many applications the process of generating label information is expensive\nand time consuming. We present a new method that combines active and\nsemi-supervised deep learning to achieve high generalization performance from a\ndeep convolutional neural network with as few known labels as possible. In a\nsetting where a small amount of labeled data as well as a large amount of\nunlabeled data is available, our method first learns the labeled data set. This\ninitialization is followed by an expectation maximization algorithm, where\nfurther training reduces classification entropy on the unlabeled data by\ntargeting a low entropy fit which is consistent with the labeled data. In\naddition the algorithm asks at a specified frequency an oracle for labels of\ndata with entropy above a certain entropy quantile. Using this active learning\ncomponent we obtain an agile labeling process that achieves high accuracy, but\nrequires only a small amount of known labels. For the MNIST dataset we report\nan error rate of 2.06% using only 300 labels and 1.06% for 1000 labels. These\nresults are obtained without employing any special network architecture or data\naugmentation.","url_abs":"http://arxiv.org/abs/1803.01216v1","url_pdf":"http://arxiv.org/pdf/1803.01216v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-bayesian-active-semi-supervised-learning","repo_url":"https://github.com/mrottmann/DeepBASS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}