{"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/non-parametric-outlier-synthesis","title":"Non-Parametric Outlier Synthesis","arxiv_id":"2303.02966","date":"2023-03-06","proceeding":null,"authors":["Leitian Tao","Xuefeng Du","Xiaojin Zhu","Yixuan Li"],"abstract":"Out-of-distribution (OOD) detection is indispensable for safely deploying machine learning models in the wild. One of the key challenges is that models lack supervision signals from unknown data, and as a result, can produce overconfident predictions on OOD data. Recent work on outlier synthesis modeled the feature space as parametric Gaussian distribution, a strong and restrictive assumption that might not hold in reality. In this paper, we propose a novel framework, Non-Parametric Outlier Synthesis (NPOS), which generates artificial OOD training data and facilitates learning a reliable decision boundary between ID and OOD data. Importantly, our proposed synthesis approach does not make any distributional assumption on the ID embeddings, thereby offering strong flexibility and generality. We show that our synthesis approach can be mathematically interpreted as a rejection sampling framework. Extensive experiments show that NPOS can achieve superior OOD detection performance, outperforming the competitive rivals by a significant margin. Code is publicly available at https://github.com/deeplearning-wisc/npos.","url_abs":"https://arxiv.org/abs/2303.02966v1","url_pdf":"https://arxiv.org/pdf/2303.02966v1.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":"non-parametric-outlier-synthesis","repo_url":"https://github.com/deeplearning-wisc/npos","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"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-imagenet-1k-12","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs Curated OODs (avg.)","model":"NPOS","rank_in_archive_order":9,"of":16,"metrics":{"AUROC":"91.22","FPR95":"37.93"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-9","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs Places","model":"NPOS","rank_in_archive_order":11,"of":25,"metrics":{"AUROC":"89.44","FPR95":"45.27"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-8","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs SUN","model":"NPOS","rank_in_archive_order":12,"of":22,"metrics":{"AUROC":"90.44","FPR95":"43.77"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-10","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs Textures","model":"NPOS","rank_in_archive_order":21,"of":34,"metrics":{"AUROC":"88.80","FPR95":"46.12"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-3","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs iNaturalist","model":"NPOS","rank_in_archive_order":14,"of":28,"metrics":{"AUROC":"96.19","FPR95":"16.58"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.02966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.02966"}},"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":"deterministic:regex_extraction","url":"https://github.com/deeplearning-wisc/npos","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":"7598fb854478a82f","entry":"SupUniformLoss","repo":"deeplearning-wisc/npos","repo_kind":"official","path":"training_from_scratch/utils/losses.py","file_url":"https://github.com/deeplearning-wisc/npos/blob/HEAD/training_from_scratch/utils/losses.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":"7598fb854478a82f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}