{"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/rethinking-the-evaluation-of-out-of","title":"Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox","arxiv_id":"2406.09867","date":"2024-06-14","proceeding":null,"authors":["Xingming Long","Jie Zhang","Shiguang Shan","Xilin Chen"],"abstract":"Most existing out-of-distribution (OOD) detection benchmarks classify samples with novel labels as the OOD data. However, some marginal OOD samples actually have close semantic contents to the in-distribution (ID) sample, which makes determining the OOD sample a Sorites Paradox. In this paper, we construct a benchmark named Incremental Shift OOD (IS-OOD) to address the issue, in which we divide the test samples into subsets with different semantic and covariate shift degrees relative to the ID dataset. The data division is achieved through a shift measuring method based on our proposed Language Aligned Image feature Decomposition (LAID). Moreover, we construct a Synthetic Incremental Shift (Syn-IS) dataset that contains high-quality generated images with more diverse covariate contents to complement the IS-OOD benchmark. We evaluate current OOD detection methods on our benchmark and find several important insights: (1) The performance of most OOD detection methods significantly improves as the semantic shift increases; (2) Some methods like GradNorm may have different OOD detection mechanisms as they rely less on semantic shifts to make decisions; (3) Excessive covariate shifts in the image are also likely to be considered as OOD for some methods. Our code and data are released in https://github.com/qqwsad5/IS-OOD.","url_abs":"https://arxiv.org/abs/2406.09867v3","url_pdf":"https://arxiv.org/pdf/2406.09867v3.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":"rethinking-the-evaluation-of-out-of","repo_url":"https://github.com/qqwsad5/is-ood","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"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":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.09867","atlas_url":"https://app.syntology.ai/?focus=2406.09867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09867"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/qqwsad5/IS-OOD","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qqwsad5/is-ood","reach":{"status":"ok"}}],"summary":{"ran":5,"ran_fixture":2,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":8,"samples":[{"code_sha256_prefix":"b78de58660ae49c7","entry":"ASHPostprocessor","repo":"qqwsad5/is-ood","repo_kind":"official","path":"openood/postprocessors/ash_postprocessor.py","file_url":"https://github.com/qqwsad5/is-ood/blob/HEAD/openood/postprocessors/ash_postprocessor.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":"b78de58660ae49c7"}},{"code_sha256_prefix":"3bde09574ad009e3","entry":"ash_b","repo":"qqwsad5/IS-OOD","repo_kind":"official","path":"openood/networks/ash_net.py","file_url":"https://github.com/qqwsad5/IS-OOD/blob/HEAD/openood/networks/ash_net.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3bde09574ad009e3"}},{"code_sha256_prefix":"e66910fd66299eb9","entry":"ash_p","repo":"qqwsad5/IS-OOD","repo_kind":"official","path":"openood/networks/ash_net.py","file_url":"https://github.com/qqwsad5/IS-OOD/blob/HEAD/openood/networks/ash_net.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e66910fd66299eb9"}},{"code_sha256_prefix":"5b873af1f2983f2d","entry":"ash_s","repo":"qqwsad5/IS-OOD","repo_kind":"official","path":"openood/networks/ash_net.py","file_url":"https://github.com/qqwsad5/IS-OOD/blob/HEAD/openood/networks/ash_net.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5b873af1f2983f2d"}},{"code_sha256_prefix":"27c636c26c1c2f18","entry":"auc_and_fpr_recall","repo":"qqwsad5/IS-OOD","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/qqwsad5/IS-OOD/blob/HEAD/evaluate.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"27c636c26c1c2f18"}},{"code_sha256_prefix":"ab6e565744fa6458","entry":"compute_all_metrics","repo":"qqwsad5/IS-OOD","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/qqwsad5/IS-OOD/blob/HEAD/evaluate.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":"ab6e565744fa6458"}},{"code_sha256_prefix":"f2ff9ff6157c2042","entry":"eval_ood","repo":"qqwsad5/IS-OOD","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/qqwsad5/IS-OOD/blob/HEAD/evaluate.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":"f2ff9ff6157c2042"}},{"code_sha256_prefix":"94aff687fee7a62b","entry":"get_id_ood_dataloader_level_split","repo":"qqwsad5/IS-OOD","repo_kind":"official","path":"datasets.py","file_url":"https://github.com/qqwsad5/IS-OOD/blob/HEAD/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"94aff687fee7a62b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}