{"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/rethinking-deep-active-learning-using-1","title":"Rethinking deep active learning: Using unlabeled data at model training","arxiv_id":"1911.08177","date":"2019-11-19","proceeding":null,"authors":["Oriane Siméoni","Mateusz Budnik","Yannis Avrithis","Guillaume Gravier"],"abstract":"Active learning typically focuses on training a model on few labeled examples alone, while unlabeled ones are only used for acquisition. In this work we depart from this setting by using both labeled and unlabeled data during model training across active learning cycles. We do so by using unsupervised feature learning at the beginning of the active learning pipeline and semi-supervised learning at every active learning cycle, on all available data. The former has not been investigated before in active learning, while the study of latter in the context of deep learning is scarce and recent findings are not conclusive with respect to its benefit. Our idea is orthogonal to acquisition strategies by using more data, much like ensemble methods use more models. By systematically evaluating on a number of popular acquisition strategies and datasets, we find that the use of unlabeled data during model training brings a surprising accuracy improvement in image classification, compared to the differences between acquisition strategies. We thus explore smaller label budgets, even one label per class.","url_abs":"https://arxiv.org/abs/1911.08177v1","url_pdf":"https://arxiv.org/pdf/1911.08177v1.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":"rethinking-deep-active-learning-using-1","repo_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.08177","atlas_url":"https://app.syntology.ai/?focus=1911.08177","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08177"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/osimeoni/RethinkingDeepActiveLearning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran_draft_wrong":1,"unverified":18},"by_repo_kind":{"official":{"samples":21,"ran":3,"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":"3fb68ed6809a8085","entry":"sigmoid_rampup","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/ramps.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/ramps.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3fb68ed6809a8085"}},{"code_sha256_prefix":"214e4ee9afcfa0e3","entry":"cosine_rampdown","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/ramps.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/ramps.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"214e4ee9afcfa0e3"}},{"code_sha256_prefix":"0182e8a61631b045","entry":"normalize_connection_graph","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/diffusion.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/diffusion.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0182e8a61631b045"}},{"code_sha256_prefix":"b644c92f19b17c62","entry":"args_def","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/parse_args.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/parse_args.py","link_basis":"first_harvest_node","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":"b644c92f19b17c62"}},{"code_sha256_prefix":"eb00239afa626c47","entry":"arrange_clustering","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/pretraining.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/pretraining.py","link_basis":"first_harvest_node","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":"eb00239afa626c47"}},{"code_sha256_prefix":"61ad799063fb382f","entry":"cg_diffusion","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/diffusion.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/diffusion.py","link_basis":"first_harvest_node","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":"61ad799063fb382f"}},{"code_sha256_prefix":"b4e42d5d1f365191","entry":"cg_diffusion_sel","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/diffusion.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/diffusion.py","link_basis":"first_harvest_node","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":"b4e42d5d1f365191"}},{"code_sha256_prefix":"c2b960cfb8e3e5e5","entry":"from_args_to_string","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/parse_args.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/parse_args.py","link_basis":"first_harvest_node","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":"c2b960cfb8e3e5e5"}},{"code_sha256_prefix":"ca3060b255d2379d","entry":"get_checkpoint_cycle_epoch","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/checkpoints.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/checkpoints.py","link_basis":"first_harvest_node","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":"ca3060b255d2379d"}},{"code_sha256_prefix":"768bffc1d686fdc1","entry":"get_unlabeled_idx","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/selection_methods.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/selection_methods.py","link_basis":"first_harvest_node","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":"768bffc1d686fdc1"}},{"code_sha256_prefix":"52ce43e6a4cb29fd","entry":"iterate_eternally_weighted","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/samplers.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/samplers.py","link_basis":"first_harvest_node","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":"52ce43e6a4cb29fd"}},{"code_sha256_prefix":"4232c309adddf9e4","entry":"iterate_once","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/samplers.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/samplers.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":"4232c309adddf9e4"}},{"code_sha256_prefix":"c0409a72750ab70d","entry":"iterate_once_weighted","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/samplers.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/samplers.py","link_basis":"first_harvest_node","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":"c0409a72750ab70d"}},{"code_sha256_prefix":"069122bd5268cc56","entry":"linear_rampup","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/ramps.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/ramps.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":"069122bd5268cc56"}},{"code_sha256_prefix":"027cbb8a99163f3d","entry":"load_best_model","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/checkpoints.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/checkpoints.py","link_basis":"first_harvest_node","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":"027cbb8a99163f3d"}},{"code_sha256_prefix":"46ba2181ef7b8680","entry":"load_checkpoint","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/checkpoints.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/checkpoints.py","link_basis":"first_harvest_node","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":"46ba2181ef7b8680"}},{"code_sha256_prefix":"f71bd22cd58c9889","entry":"preprocess_features","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/pretraining.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/pretraining.py","link_basis":"first_harvest_node","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":"f71bd22cd58c9889"}},{"code_sha256_prefix":"06cfd1a81374ad1f","entry":"relabel_dataset","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/data.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/data.py","link_basis":"first_harvest_node","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":"06cfd1a81374ad1f"}},{"code_sha256_prefix":"241d2900db767278","entry":"run_kmeans","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/pretraining.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/pretraining.py","link_basis":"first_harvest_node","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":"241d2900db767278"}},{"code_sha256_prefix":"9504dfabd495b1d0","entry":"update_dataset","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/data.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/data.py","link_basis":"first_harvest_node","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":"9504dfabd495b1d0"}},{"code_sha256_prefix":"536b69ff13eb7ad5","entry":"update_dataset_resuming","repo":"osimeoni/RethinkingDeepActiveLearning","repo_kind":"official","path":"lib/data.py","file_url":"https://github.com/osimeoni/RethinkingDeepActiveLearning/blob/HEAD/lib/data.py","link_basis":"first_harvest_node","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":"536b69ff13eb7ad5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}