{"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/vos-learning-what-you-don-t-know-by-virtual","title":"VOS: Learning What You Don't Know by Virtual Outlier Synthesis","arxiv_id":"2202.01197","date":"2022-02-02","proceeding":null,"authors":["Xuefeng Du","Zhaoning Wang","Mu Cai","Yixuan Li"],"abstract":"Out-of-distribution (OOD) detection has received much attention lately due to its importance in the safe deployment of neural networks. 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. Previous approaches rely on real outlier datasets for model regularization, which can be costly and sometimes infeasible to obtain in practice. In this paper, we present VOS, a novel framework for OOD detection by adaptively synthesizing virtual outliers that can meaningfully regularize the model's decision boundary during training. Specifically, VOS samples virtual outliers from the low-likelihood region of the class-conditional distribution estimated in the feature space. Alongside, we introduce a novel unknown-aware training objective, which contrastively shapes the uncertainty space between the ID data and synthesized outlier data. VOS achieves competitive performance on both object detection and image classification models, reducing the FPR95 by up to 9.36% compared to the previous best method on object detectors. Code is available at https://github.com/deeplearning-wisc/vos.","url_abs":"https://arxiv.org/abs/2202.01197v4","url_pdf":"https://arxiv.org/pdf/2202.01197v4.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":"vos-learning-what-you-don-t-know-by-virtual","repo_url":"https://github.com/deeplearning-wisc/vos","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"vos-learning-what-you-don-t-know-by-virtual","repo_url":"https://github.com/kostadinovshalon/oln-ssos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"ood-detection","task_name":"Out of Distribution (OOD) Detection"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"vos","method_name":"VOS"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2202.01197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.01197"}},"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/vos","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kostadinovshalon/oln-ssos","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"ran_honours":1},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":0,"samples":[{"code_sha256_prefix":"17bbd961aaf86569","entry":"ODIN","repo":"deeplearning-wisc/vos","repo_kind":"official","path":"classification/utils/score_calculation.py","file_url":"https://github.com/deeplearning-wisc/vos/blob/HEAD/classification/utils/score_calculation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"17bbd961aaf86569"}},{"code_sha256_prefix":"1134ab62338793e2","entry":"fpr_and_fdr_at_recall","repo":"deeplearning-wisc/vos","repo_kind":"official","path":"metric_utils.py","file_url":"https://github.com/deeplearning-wisc/vos/blob/HEAD/metric_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1134ab62338793e2"}},{"code_sha256_prefix":"24f5b40495bb542e","entry":"get_Mahalanobis_score","repo":"deeplearning-wisc/vos","repo_kind":"official","path":"classification/utils/score_calculation.py","file_url":"https://github.com/deeplearning-wisc/vos/blob/HEAD/classification/utils/score_calculation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"24f5b40495bb542e"}},{"code_sha256_prefix":"9b1abfca5a67be06","entry":"get_measures","repo":"deeplearning-wisc/vos","repo_kind":"official","path":"metric_utils.py","file_url":"https://github.com/deeplearning-wisc/vos/blob/HEAD/metric_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9b1abfca5a67be06"}},{"code_sha256_prefix":"3ad01de2f86dccba","entry":"get_ood_scores_odin","repo":"deeplearning-wisc/vos","repo_kind":"official","path":"classification/utils/score_calculation.py","file_url":"https://github.com/deeplearning-wisc/vos/blob/HEAD/classification/utils/score_calculation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ad01de2f86dccba"}},{"code_sha256_prefix":"d4acb3120a027622","entry":"stable_cumsum","repo":"deeplearning-wisc/vos","repo_kind":"official","path":"metric_utils.py","file_url":"https://github.com/deeplearning-wisc/vos/blob/HEAD/metric_utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d4acb3120a027622"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}