{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/open-world-semi-supervised-learning-1","title":"Open-World Semi-Supervised Learning","arxiv_id":"2102.03526","date":"2021-02-06","proceeding":"ICLR 2022 4","authors":["Kaidi Cao","Maria Brbic","Jure Leskovec"],"abstract":"A fundamental limitation of applying semi-supervised learning in real-world settings is the assumption that unlabeled test data contains only classes previously encountered in the labeled training data. However, this assumption rarely holds for data in-the-wild, where instances belonging to novel classes may appear at testing time. Here, we introduce a novel open-world semi-supervised learning setting that formalizes the notion that novel classes may appear in the unlabeled test data. In this novel setting, the goal is to solve the class distribution mismatch between labeled and unlabeled data, where at the test time every input instance either needs to be classified into one of the existing classes or a new unseen class needs to be initialized. To tackle this challenging problem, we propose ORCA, an end-to-end deep learning approach that introduces uncertainty adaptive margin mechanism to circumvent the bias towards seen classes caused by learning discriminative features for seen classes faster than for the novel classes. In this way, ORCA reduces the gap between intra-class variance of seen with respect to novel classes. Experiments on image classification datasets and a single-cell annotation dataset demonstrate that ORCA consistently outperforms alternative baselines, achieving 25% improvement on seen and 96% improvement on novel classes of the ImageNet dataset.","url_abs":"https://arxiv.org/abs/2102.03526v3","url_pdf":"https://arxiv.org/pdf/2102.03526v3.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":"open-world-semi-supervised-learning-1","repo_url":"https://github.com/snap-stanford/orca","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"novel-object-detection","task_name":"Novel Object Detection"},{"task_slug":"open-world-semi-supervised-learning","task_name":"Open-World Semi-Supervised Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/novel-object-detection-on-lvis-v1-0-val","task":"Novel Object Detection","dataset":"LVIS v1.0 val","model":"ORCA Cao et al. (2022)","rank_in_archive_order":4,"of":5,"metrics":{"All mAP":"2.03","Known mAP":"20.57","Novel mAP":"0.49"},"uses_additional_data":false},{"leaderboard":"/sota/open-world-semi-supervised-learning-on-cifar","task":"Open-World Semi-Supervised Learning","dataset":"CIFAR-10","model":"ORCA (ResNet-18)","rank_in_archive_order":3,"of":5,"metrics":{"All accuracy (10% Labeled)":"84.1","All accuracy (50% Labeled)":"89.7","Novel accuracy (10% Labeled)":"85.5","Novel accuracy (50% Labeled)":"90.4","Seen accuracy (10% Labeled)":"82.8","Seen accuracy (50% Labeled)":"88.2"},"uses_additional_data":false},{"leaderboard":"/sota/open-world-semi-supervised-learning-on-cifar-1","task":"Open-World Semi-Supervised Learning","dataset":"CIFAR-100","model":"ORCA (ResNet-18)","rank_in_archive_order":3,"of":3,"metrics":{"All accuracy (10% Labeled)":"38.6","All accuracy (50% Labeled)":"48.1","Novel accuracy (10% Labeled)":"31.8","Novel accuracy (50% Labeled)":"43.0","Seen accuracy (10% Labeled)":"52.5","Seen accuracy (50% Labeled)":"66.9"},"uses_additional_data":false},{"leaderboard":"/sota/open-world-semi-supervised-learning-on-1","task":"Open-World Semi-Supervised Learning","dataset":"ImageNet-100 (TEMI Split)","model":"ORCA (ResNet-50)","rank_in_archive_order":2,"of":5,"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}],"syntology":{"syntology_url":"https://syntology.ai/paper/2102.03526","atlas_url":"https://app.syntology.ai/?focus=2102.03526","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2102.03526"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2102.03526\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2102.03526"},"call":"get_concepts_for_paper(arxiv_id=\"2102.03526\")"}],"by_repo":[{"repo":"snap-stanford/orca","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"6869b705f8fc7bbed879520234fa52050f729365c091340537f2cea98eb127c7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}