{"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/temporal-ensembling-for-semi-supervised","title":"Temporal Ensembling for Semi-Supervised Learning","arxiv_id":"1610.02242","date":"2016-10-07","proceeding":null,"authors":["Samuli Laine","Timo Aila"],"abstract":"In this paper, we present a simple and efficient method for training deep\nneural networks in a semi-supervised setting where only a small portion of\ntraining data is labeled. We introduce self-ensembling, where we form a\nconsensus prediction of the unknown labels using the outputs of the\nnetwork-in-training on different epochs, and most importantly, under different\nregularization and input augmentation conditions. This ensemble prediction can\nbe expected to be a better predictor for the unknown labels than the output of\nthe network at the most recent training epoch, and can thus be used as a target\nfor training. Using our method, we set new records for two standard\nsemi-supervised learning benchmarks, reducing the (non-augmented)\nclassification error rate from 18.44% to 7.05% in SVHN with 500 labels and from\n18.63% to 16.55% in CIFAR-10 with 4000 labels, and further to 5.12% and 12.16%\nby enabling the standard augmentations. We additionally obtain a clear\nimprovement in CIFAR-100 classification accuracy by using random images from\nthe Tiny Images dataset as unlabeled extra inputs during training. Finally, we\ndemonstrate good tolerance to incorrect labels.","url_abs":"http://arxiv.org/abs/1610.02242v3","url_pdf":"http://arxiv.org/pdf/1610.02242v3.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":"temporal-ensembling-for-semi-supervised","repo_url":"https://github.com/smlaine2/tempens","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"temporal-ensembling-for-semi-supervised","repo_url":"https://github.com/ambujojha/SemiSupervisedLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"temporal-ensembling-for-semi-supervised","repo_url":"https://github.com/benathi/fastswa-semi-sup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"temporal-ensembling-for-semi-supervised","repo_url":"https://github.com/geosada/pi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"temporal-ensembling-for-semi-supervised","repo_url":"https://github.com/hiram64/temporal-ensembling-semi-supervised","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"temporal-ensembling-for-semi-supervised","repo_url":"https://github.com/notha99y/mean_teacher_domain_adapt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"temporal-ensembling-for-semi-supervised","repo_url":"https://github.com/tensorfreitas/Temporal-Ensembling-for-Semi-Supervised-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-6","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 250 Labels","model":"Ⅱ-Model","rank_in_archive_order":27,"of":27,"metrics":{"Percentage error":"53.12"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 4000 Labels","model":"Pi Model","rank_in_archive_order":45,"of":49,"metrics":{"Percentage error":"12.16"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-2","task":"Semi-Supervised Image Classification","dataset":"cifar-100, 10000 Labels","model":"Temporal ensembling","rank_in_archive_order":27,"of":29,"metrics":{"Percentage error":"38.65"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1610.02242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.02242"}},"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/notha99y/mean_teacher_domain_adapt","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/geosada/pi","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ambujojha/SemiSupervisedLearning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorfreitas/Temporal-Ensembling-for-Semi-Supervised-Learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hiram64/temporal-ensembling-semi-supervised","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/benathi/fastswa-semi-sup","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/smlaine2/tempens","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran":2,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"listed":{"samples":7,"ran":3,"repositories":5}},"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":2,"samples":[{"code_sha256_prefix":"419f8b719773c8bb","entry":"Layers","repo":"geosada/pi","repo_kind":"listed","path":"PI.py","file_url":"https://github.com/geosada/pi/blob/HEAD/PI.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"419f8b719773c8bb"}},{"code_sha256_prefix":"aa7ea344f0434be4","entry":"WeightEMA","repo":"benathi/fastswa-semi-sup","repo_kind":"listed","path":"mean_teacher/optim_weight_ema.py","file_url":"https://github.com/benathi/fastswa-semi-sup/blob/HEAD/mean_teacher/optim_weight_ema.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aa7ea344f0434be4"}},{"code_sha256_prefix":"400d36e0fcd2632d","entry":"update_unsupervised_target","repo":"hiram64/temporal-ensembling-semi-supervised","repo_kind":"listed","path":"lib/ops.py","file_url":"https://github.com/hiram64/temporal-ensembling-semi-supervised/blob/HEAD/lib/ops.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"400d36e0fcd2632d"}},{"code_sha256_prefix":"b148a31fddf9565e","entry":"LossFunctions","repo":"geosada/pi","repo_kind":"listed","path":"PI.py","file_url":"https://github.com/geosada/pi/blob/HEAD/PI.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b148a31fddf9565e"}},{"code_sha256_prefix":"6578002d5d292065","entry":"PI","repo":"geosada/pi","repo_kind":"listed","path":"PI.py","file_url":"https://github.com/geosada/pi/blob/HEAD/PI.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6578002d5d292065"}},{"code_sha256_prefix":"88874fb38feaf13a","entry":"ema","repo":"notha99y/mean_teacher_domain_adapt","repo_kind":"listed","path":"src/model.py","file_url":"https://github.com/notha99y/mean_teacher_domain_adapt/blob/HEAD/src/model.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":"88874fb38feaf13a"}},{"code_sha256_prefix":"2fa6b82b8cbfe7b4","entry":"temporal_ensembling_loss","repo":"tensorfreitas/Temporal-Ensembling-for-Semi-Supervised-Learning","repo_kind":"listed","path":"pi_model.py","file_url":"https://github.com/tensorfreitas/Temporal-Ensembling-for-Semi-Supervised-Learning/blob/HEAD/pi_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2fa6b82b8cbfe7b4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}