{"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/meta-co-training-two-views-are-better-than","title":"Meta Co-Training: Two Views are Better than One","arxiv_id":"2311.18083","date":"2023-11-29","proceeding":null,"authors":["Jay C. Rothenberger","Dimitrios I. Diochnos"],"abstract":"In many practical computer vision scenarios unlabeled data is plentiful, but labels are scarce and difficult to obtain. As a result, semi-supervised learning which leverages unlabeled data to boost the performance of supervised classifiers have received significant attention in recent literature. One major class of semi-supervised algorithms is co-training. In co-training two different models leverage different independent and sufficient \"views\" of the data to jointly make better predictions. During co-training each model creates pseudo labels on unlabeled points which are used to improve the other model. We show that in the common case when independent views are not available we can construct such views inexpensively using pre-trained models. Co-training on the constructed views yields a performance improvement over any of the individual views we construct and performance comparable with recent approaches in semi-supervised learning, but has some undesirable properties. To alleviate the issues present with co-training we present Meta Co-Training which is an extension of the successful Meta Pseudo Labels approach to two views. Our method achieves new state-of-the-art performance on ImageNet-10% with very few training resources, as well as outperforming prior semi-supervised work on several other fine-grained image classification datasets.","url_abs":"https://arxiv.org/abs/2311.18083v4","url_pdf":"https://arxiv.org/pdf/2311.18083v4.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":"meta-co-training-two-views-are-better-than","repo_url":"https://github.com/jayrothenberger/meta-co-training","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"meta-pseudo-labels","method_name":"Meta Pseudo Labels"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"Meta Co-Training","rank_in_archive_order":4,"of":65,"metrics":{"Top 1 Accuracy":"80.7%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"Meta Co-Training","rank_in_archive_order":2,"of":75,"metrics":{"Top 1 Accuracy":"85.8%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2311.18083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18083"}},"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/jayrothenberger/meta-co-training","reach":null}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"145a8c186a34ba42","entry":"make_loader","repo":"jayrothenberger/meta-co-training","repo_kind":"official","path":"meta-cotraining/src/mct/MCT.py","file_url":"https://github.com/jayrothenberger/meta-co-training/blob/HEAD/meta-cotraining/src/mct/MCT.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":"145a8c186a34ba42"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}