{"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-learning-with-image-data","title":"Deep Bayesian Active Learning with Image Data","arxiv_id":"1703.02910","date":"2017-03-08","proceeding":"ICML 2017 8","authors":["Yarin Gal","Riashat Islam","Zoubin Ghahramani"],"abstract":"Even though active learning forms an important pillar of machine learning,\ndeep learning tools are not prevalent within it. Deep learning poses several\ndifficulties when used in an active learning setting. First, active learning\n(AL) methods generally rely on being able to learn and update models from small\namounts of data. Recent advances in deep learning, on the other hand, are\nnotorious for their dependence on large amounts of data. Second, many AL\nacquisition functions rely on model uncertainty, yet deep learning methods\nrarely represent such model uncertainty. In this paper we combine recent\nadvances in Bayesian deep learning into the active learning framework in a\npractical way. We develop an active learning framework for high dimensional\ndata, a task which has been extremely challenging so far, with very sparse\nexisting literature. Taking advantage of specialised models such as Bayesian\nconvolutional neural networks, we demonstrate our active learning techniques\nwith image data, obtaining a significant improvement on existing active\nlearning approaches. We demonstrate this on both the MNIST dataset, as well as\nfor skin cancer diagnosis from lesion images (ISIC2016 task).","url_abs":"http://arxiv.org/abs/1703.02910v1","url_pdf":"http://arxiv.org/pdf/1703.02910v1.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-learning-with-image-data","repo_url":"https://github.com/aolmin/active_learning_weak_sup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-bayesian-active-learning-with-image-data","repo_url":"https://github.com/bonaventuredossou/ece526_course_project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"deep-bayesian-active-learning-with-image-data","repo_url":"https://github.com/tanyanair/segmentation_uncertainty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-bayesian-active-learning-with-image-data","repo_url":"https://github.com/Riashat/Active-Learning-Bayesian-Convolutional-Neural-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deep-bayesian-active-learning-with-image-data","repo_url":"https://github.com/damienlancry/DBAL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"deep-bayesian-active-learning-with-image-data","repo_url":"https://github.com/dsba-lab/openal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.02910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.02910"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bonaventuredossou/ece526_course_project","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aolmin/active_learning_weak_sup","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tanyanair/segmentation_uncertainty","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dsba-lab/openal","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/damienlancry/DBAL","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Riashat/Active-Learning-Bayesian-Convolutional-Neural-Networks","reach":{"status":"ok"}}],"summary":{"unverified":7},"by_repo_kind":{"listed":{"samples":7,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2c7f16163e5c52da","entry":"bald_acquisition","repo":"aolmin/active_learning_weak_sup","repo_kind":"listed","path":"src/GP_Bald.py","file_url":"https://github.com/aolmin/active_learning_weak_sup/blob/HEAD/src/GP_Bald.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2c7f16163e5c52da"}},{"code_sha256_prefix":"dae1d4c962119957","entry":"bald_ws_acquisition","repo":"aolmin/active_learning_weak_sup","repo_kind":"listed","path":"src/GP_Bald_WS.py","file_url":"https://github.com/aolmin/active_learning_weak_sup/blob/HEAD/src/GP_Bald_WS.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dae1d4c962119957"}},{"code_sha256_prefix":"a99a96e5b037d914","entry":"constant_noise","repo":"aolmin/active_learning_weak_sup","repo_kind":"listed","path":"src/experiment_utils.py","file_url":"https://github.com/aolmin/active_learning_weak_sup/blob/HEAD/src/experiment_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a99a96e5b037d914"}},{"code_sha256_prefix":"2522288f1d9bdc50","entry":"get_sine_regression_data","repo":"aolmin/active_learning_weak_sup","repo_kind":"listed","path":"src/experiment_utils.py","file_url":"https://github.com/aolmin/active_learning_weak_sup/blob/HEAD/src/experiment_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2522288f1d9bdc50"}},{"code_sha256_prefix":"4f1c06eb0624ab33","entry":"mi_ws_acquisition","repo":"aolmin/active_learning_weak_sup","repo_kind":"listed","path":"src/GP_MI_WS.py","file_url":"https://github.com/aolmin/active_learning_weak_sup/blob/HEAD/src/GP_MI_WS.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4f1c06eb0624ab33"}},{"code_sha256_prefix":"2d8f788261c688a7","entry":"random_acquisition","repo":"aolmin/active_learning_weak_sup","repo_kind":"listed","path":"src/Random.py","file_url":"https://github.com/aolmin/active_learning_weak_sup/blob/HEAD/src/Random.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d8f788261c688a7"}},{"code_sha256_prefix":"c25e60c784a9f6bc","entry":"sine_regression_data_sample_input","repo":"aolmin/active_learning_weak_sup","repo_kind":"listed","path":"src/experiment_utils.py","file_url":"https://github.com/aolmin/active_learning_weak_sup/blob/HEAD/src/experiment_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c25e60c784a9f6bc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}