{"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/generalized-out-of-distribution-detection-a","title":"Generalized Out-of-Distribution Detection: A Survey","arxiv_id":"2110.11334","date":"2021-10-21","proceeding":null,"authors":["Jingkang Yang","Kaiyang Zhou","Yixuan Li","Ziwei Liu"],"abstract":"Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of machine learning systems. For instance, in autonomous driving, we would like the driving system to issue an alert and hand over the control to humans when it detects unusual scenes or objects that it has never seen during training time and cannot make a safe decision. The term, OOD detection, first emerged in 2017 and since then has received increasing attention from the research community, leading to a plethora of methods developed, ranging from classification-based to density-based to distance-based ones. Meanwhile, several other problems, including anomaly detection (AD), novelty detection (ND), open set recognition (OSR), and outlier detection (OD), are closely related to OOD detection in terms of motivation and methodology. Despite common goals, these topics develop in isolation, and their subtle differences in definition and problem setting often confuse readers and practitioners. In this survey, we first present a unified framework called generalized OOD detection, which encompasses the five aforementioned problems, i.e., AD, ND, OSR, OOD detection, and OD. Under our framework, these five problems can be seen as special cases or sub-tasks, and are easier to distinguish. We then review each of these five areas by summarizing their recent technical developments, with a special focus on OOD detection methodologies. We conclude this survey with open challenges and potential research directions.","url_abs":"https://arxiv.org/abs/2110.11334v3","url_pdf":"https://arxiv.org/pdf/2110.11334v3.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":"generalized-out-of-distribution-detection-a","repo_url":"https://github.com/jingkang50/oodsurvey","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"generalized-out-of-distribution-detection-a","repo_url":"https://github.com/jingkang50/openood","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"generalized-out-of-distribution-detection-a","repo_url":"https://github.com/adverml/advopenood","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"generalized-out-of-distribution-detection-a","repo_url":"https://github.com/antoinedemathelin/openood","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"novelty-detection","task_name":"Novelty Detection"},{"task_slug":"open-set-learning","task_name":"Open Set Learning"},{"task_slug":"ood-detection","task_name":"Out of Distribution (OOD) Detection"},{"task_slug":"out-of-distribution-detection","task_name":"Out-of-Distribution Detection"},{"task_slug":"outlier-detection","task_name":"Outlier Detection"},{"task_slug":"survey","task_name":"Survey"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.11334","atlas_url":"https://app.syntology.ai/?focus=2110.11334","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":"2110.11334"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2110.11334\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2110.11334"},"call":"get_concepts_for_paper(arxiv_id=\"2110.11334\")"}],"by_repo":[{"repo":"jingkang50/oodsurvey","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jingkang50/openood","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2203.10807","2309.14888"],"harvested_for_calls":[{"arxiv_id":"2203.10807","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.10807"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.10807\")"},{"arxiv_id":"2309.14888","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2309.14888"},"call":"get_harvested_code_for_paper(arxiv_id=\"2309.14888\")"}]},{"repo":"adverml/advopenood","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2210.07242","2406.15104"],"harvested_for_calls":[{"arxiv_id":"2210.07242","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.07242"},"call":"get_harvested_code_for_paper(arxiv_id=\"2210.07242\")"},{"arxiv_id":"2406.15104","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2406.15104"},"call":"get_harvested_code_for_paper(arxiv_id=\"2406.15104\")"}]},{"repo":"antoinedemathelin/openood","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2210.07242"],"harvested_for_calls":[{"arxiv_id":"2210.07242","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.07242"},"call":"get_harvested_code_for_paper(arxiv_id=\"2210.07242\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"1215fc6c694f9fe798ea59f5ff17ba4ee5d028aa50ae02f5ee89b42466ef9403","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}