{"url":"/sota/open-world-semi-supervised-learning-on-1","task":{"name":"Open-World Semi-Supervised Learning","url":"/task/open-world-semi-supervised-learning","note":null},"dataset":{"name":"ImageNet-100 (TEMI Split)","url":"/dataset/imagenet-100"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Novel accuracy (50% Labeled)","Seen accuracy (50% Labeled)","All accuracy (50% Labeled)","All accuracy (10% Labeled)","Novel accuracy (10% Labeled)","Seen accuracy (10% Labeled)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Novel accuracy (50% Labeled)":"higher","Seen accuracy (50% Labeled)":"higher","All accuracy (50% Labeled)":"higher","All accuracy (10% Labeled)":"higher","Novel accuracy (10% Labeled)":"higher","Seen accuracy (10% Labeled)":"higher"}},"counts":{"rows":5,"rows_with_code":5,"rows_with_paper_page":5,"rows_dated":5,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SimGCD (ViT-B-16)","metrics":{"All accuracy (50% Labeled)":"83.6","Novel accuracy (50% Labeled)":"79.1","Seen accuracy (50% Labeled)":"92.4"},"uses_additional_data":false,"paper_date":"2022-11-21","paper":"/paper/a-simple-parametric-classification-baseline","paper_url":"https://arxiv.org/abs/2211.11727v4","paper_title":"Parametric Classification for Generalized Category Discovery: A Baseline Study","code":"https://github.com/cvmi-lab/simgcd","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"ORCA (ResNet-50)","metrics":{"All accuracy (10% Labeled)":"69.7","All accuracy (50% Labeled)":"77.8","Novel accuracy (10% Labeled)":"60.5","Novel accuracy (50% Labeled)":"72.1","Seen accuracy (10% Labeled)":"83.9","Seen accuracy (50% Labeled)":"89.1"},"uses_additional_data":false,"paper_date":"2021-02-06","paper":"/paper/open-world-semi-supervised-learning-1","paper_url":"https://arxiv.org/abs/2102.03526v3","paper_title":"Open-World Semi-Supervised Learning","code":"https://github.com/snap-stanford/orca","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"OpenLDN (ResNet-50)","metrics":{"All accuracy (50% Labeled)":"79.1","Novel accuracy (50% Labeled)":"68.6","Seen accuracy (50% Labeled)":"89.6"},"uses_additional_data":false,"paper_date":"2022-07-05","paper":"/paper/openldn-learning-to-discover-novel-classes","paper_url":"https://arxiv.org/abs/2207.02261v2","paper_title":"OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning","code":"https://github.com/nayeemrizve/openldn","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"GCD (ViT-B-16)","metrics":{"All accuracy (50% Labeled)":"74.1","Novel accuracy (50% Labeled)":"66.3","Seen accuracy (50% Labeled)":"89.8"},"uses_additional_data":false,"paper_date":"2022-01-07","paper":"/paper/generalized-category-discovery","paper_url":"https://arxiv.org/abs/2201.02609v2","paper_title":"Generalized Category Discovery","code":"https://github.com/sgvaze/generalized-category-discovery","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"TRSSL (ResNet-50)","metrics":{"All accuracy (10% Labeled)":"75.4","Novel accuracy (10% Labeled)":"67.8","Seen accuracy (10% Labeled)":"82.6"},"uses_additional_data":false,"paper_date":"2022-07-05","paper":"/paper/towards-realistic-semi-supervised-learning","paper_url":"https://arxiv.org/abs/2207.02269v2","paper_title":"Towards Realistic Semi-Supervised Learning","code":"https://github.com/nayeemrizve/trssl","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":10,"n_unverified":6,"n_samples":16,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":10,"n_unverified":6,"n_samples":16,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}