{"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/learn-what-you-can-t-learn-regularized-1","title":"Semi-supervised novelty detection using ensembles with regularized disagreement","arxiv_id":"2012.05825","date":"2020-12-10","proceeding":null,"authors":["Alexandru Ţifrea","Eric Stavarache","Fanny Yang"],"abstract":"Deep neural networks often predict samples with high confidence even when they come from unseen classes and should instead be flagged for expert evaluation. Current novelty detection algorithms cannot reliably identify such near OOD points unless they have access to labeled data that is similar to these novel samples. In this paper, we develop a new ensemble-based procedure for semi-supervised novelty detection (SSND) that successfully leverages a mixture of unlabeled ID and novel-class samples to achieve good detection performance. In particular, we show how to achieve disagreement only on OOD data using early stopping regularization. While we prove this fact for a simple data distribution, our extensive experiments suggest that it holds true for more complex scenarios: our approach significantly outperforms state-of-the-art SSND methods on standard image data sets (SVHN/CIFAR-10/CIFAR-100) and medical image data sets with only a negligible increase in computation cost.","url_abs":"https://arxiv.org/abs/2012.05825v3","url_pdf":"https://arxiv.org/pdf/2012.05825v3.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":"learn-what-you-can-t-learn-regularized-1","repo_url":"https://github.com/ericpts/reto","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"novelty-detection","task_name":"Novelty Detection"},{"task_slug":"ood-detection","task_name":"Out of Distribution (OOD) Detection"},{"task_slug":"out-of-distribution-detection","task_name":"Out-of-Distribution Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/out-of-distribution-detection-on-cifar-10-vs-10","task":"Out-of-Distribution Detection","dataset":"CIFAR-10 vs CIFAR-10.1","model":"ERD (ResNet18)","rank_in_archive_order":1,"of":1,"metrics":{"AUROC":"91.4"},"uses_additional_data":true},{"leaderboard":"/sota/out-of-distribution-detection-on-cifar-10-vs","task":"Out-of-Distribution Detection","dataset":"CIFAR-10 vs CIFAR-100","model":"ERD (ResNet18)","rank_in_archive_order":8,"of":14,"metrics":{"AUROC":"95.1"},"uses_additional_data":true},{"leaderboard":"/sota/out-of-distribution-detection-on-cifar-100-vs","task":"Out-of-Distribution Detection","dataset":"CIFAR-100 vs CIFAR-10","model":"ERD (ResNet18)","rank_in_archive_order":8,"of":14,"metrics":{"AUROC":"94.3"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.05825","atlas_url":"https://app.syntology.ai/?focus=2012.05825","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":"2012.05825"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.05825\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.05825"},"call":"get_concepts_for_paper(arxiv_id=\"2012.05825\")"}],"by_repo":[{"repo":"ericpts/reto","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":"77adbb88b16c97b3c7a83b8ac7dbf1b7d84e69eaeef4cbffe4fb90bde3ce1d71","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}