{"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/in-or-out-fixing-imagenet-out-of-distribution","title":"In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation","arxiv_id":"2306.00826","date":"2023-06-01","proceeding":null,"authors":["Julian Bitterwolf","Maximilian Müller","Matthias Hein"],"abstract":"Out-of-distribution (OOD) detection is the problem of identifying inputs which are unrelated to the in-distribution task. The OOD detection performance when the in-distribution (ID) is ImageNet-1K is commonly being tested on a small range of test OOD datasets. We find that most of the currently used test OOD datasets, including datasets from the open set recognition (OSR) literature, have severe issues: In some cases more than 50$\\%$ of the dataset contains objects belonging to one of the ID classes. These erroneous samples heavily distort the evaluation of OOD detectors. As a solution, we introduce with NINCO a novel test OOD dataset, each sample checked to be ID free, which with its fine-grained range of OOD classes allows for a detailed analysis of an OOD detector's strengths and failure modes, particularly when paired with a number of synthetic \"OOD unit-tests\". We provide detailed evaluations across a large set of architectures and OOD detection methods on NINCO and the unit-tests, revealing new insights about model weaknesses and the effects of pretraining on OOD detection performance. We provide code and data at https://github.com/j-cb/NINCO.","url_abs":"https://arxiv.org/abs/2306.00826v1","url_pdf":"https://arxiv.org/pdf/2306.00826v1.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":"in-or-out-fixing-imagenet-out-of-distribution","repo_url":"https://github.com/j-cb/ninco","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"in-or-out-fixing-imagenet-out-of-distribution","repo_url":"https://github.com/robertsi20/Conceptualizing-Uncertainty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[{"slug":"imagenet-1k-vs-ninco","name":"ImageNet-1k vs NINCO","full_name":"No ImageNet Class Objects"},{"slug":"ninco","name":"NINCO","full_name":"No ImageNet Class Objects"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-13","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs NINCO","model":"ViT-B-384 Mahalanobis (pre-trained on IN-21k)","rank_in_archive_order":2,"of":5,"metrics":{"AUROC":"95.0","FPR@95":"27.5 "},"uses_additional_data":true},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-13","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs NINCO","model":"EffNetv2-M Relative Mahalanobis","rank_in_archive_order":4,"of":5,"metrics":{"AUROC":"88.9","FPR@95":"54.9 "},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-13","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs NINCO","model":"EffNetb7  Relative Cosine Sim","rank_in_archive_order":5,"of":5,"metrics":{"AUROC":"87.9","FPR@95":"53.7"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2306.00826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00826"}},"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/j-cb/NINCO","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/robertsi20/Conceptualizing-Uncertainty","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/j-cb/ninco","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"unverified":18},"by_repo_kind":{"official":{"samples":7,"ran":1,"repositories":1},"listed":{"samples":12,"ran":0,"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":"9d74dcf8506e1770","entry":"all_equal","repo":"j-cb/NINCO","repo_kind":"official","path":"detection_methods.py","file_url":"https://github.com/j-cb/NINCO/blob/HEAD/detection_methods.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9d74dcf8506e1770"}},{"code_sha256_prefix":"3d6e8aba845cd198","entry":"activation_transform","repo":"robertsi20/Conceptualizing-Uncertainty","repo_kind":"listed","path":"experiment_helpers/experiment_helper_functions.py","file_url":"https://github.com/robertsi20/Conceptualizing-Uncertainty/blob/HEAD/experiment_helpers/experiment_helper_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d6e8aba845cd198"}},{"code_sha256_prefix":"e4dd80a716476cad","entry":"auroc_ood","repo":"j-cb/NINCO","repo_kind":"official","path":"utils.py","file_url":"https://github.com/j-cb/NINCO/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e4dd80a716476cad"}},{"code_sha256_prefix":"9e50d4327bb54248","entry":"entropy_uncertainty","repo":"robertsi20/Conceptualizing-Uncertainty","repo_kind":"listed","path":"experiment_helpers/lm_experiment_helper_functions.py","file_url":"https://github.com/robertsi20/Conceptualizing-Uncertainty/blob/HEAD/experiment_helpers/lm_experiment_helper_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e50d4327bb54248"}},{"code_sha256_prefix":"0ce1ea919855558a","entry":"evaluate_MSP","repo":"j-cb/NINCO","repo_kind":"official","path":"detection_methods.py","file_url":"https://github.com/j-cb/NINCO/blob/HEAD/detection_methods.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0ce1ea919855558a"}},{"code_sha256_prefix":"1d5e0e0880eb3ef5","entry":"excerpt_fct","repo":"robertsi20/Conceptualizing-Uncertainty","repo_kind":"listed","path":"experiment_helpers/lm_experiment_helper_functions.py","file_url":"https://github.com/robertsi20/Conceptualizing-Uncertainty/blob/HEAD/experiment_helpers/lm_experiment_helper_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1d5e0e0880eb3ef5"}},{"code_sha256_prefix":"479e0fc1207ac1f5","entry":"filter_dataset_by_classes","repo":"robertsi20/Conceptualizing-Uncertainty","repo_kind":"listed","path":"experiment_helpers/.ipynb_checkpoints/experiment_helper_functions-checkpoint.py","file_url":"https://github.com/robertsi20/Conceptualizing-Uncertainty/blob/HEAD/experiment_helpers/.ipynb_checkpoints/experiment_helper_functions-checkpoint.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"479e0fc1207ac1f5"}},{"code_sha256_prefix":"d0fbaed8e9101241","entry":"kl","repo":"j-cb/NINCO","repo_kind":"official","path":"detection_methods.py","file_url":"https://github.com/j-cb/NINCO/blob/HEAD/detection_methods.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d0fbaed8e9101241"}},{"code_sha256_prefix":"f2493ae6234060d7","entry":"likelyhood","repo":"robertsi20/Conceptualizing-Uncertainty","repo_kind":"listed","path":"Uncertainty_Functions/unc_functions.py","file_url":"https://github.com/robertsi20/Conceptualizing-Uncertainty/blob/HEAD/Uncertainty_Functions/unc_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f2493ae6234060d7"}},{"code_sha256_prefix":"6249856e2176ac62","entry":"noise_pixel_permutation","repo":"j-cb/NINCO","repo_kind":"official","path":"noise_functions.py","file_url":"https://github.com/j-cb/NINCO/blob/HEAD/noise_functions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6249856e2176ac62"}},{"code_sha256_prefix":"ccb68389c662d0c5","entry":"noise_rademacher","repo":"j-cb/NINCO","repo_kind":"official","path":"noise_functions.py","file_url":"https://github.com/j-cb/NINCO/blob/HEAD/noise_functions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ccb68389c662d0c5"}},{"code_sha256_prefix":"a60d7c4d12e684cd","entry":"noise_uniform","repo":"j-cb/NINCO","repo_kind":"official","path":"noise_functions.py","file_url":"https://github.com/j-cb/NINCO/blob/HEAD/noise_functions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a60d7c4d12e684cd"}},{"code_sha256_prefix":"5eadcd84551df892","entry":"norm","repo":"robertsi20/Conceptualizing-Uncertainty","repo_kind":"listed","path":"concept_helpers/disc_nmf.py","file_url":"https://github.com/robertsi20/Conceptualizing-Uncertainty/blob/HEAD/concept_helpers/disc_nmf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5eadcd84551df892"}},{"code_sha256_prefix":"832caef4ff71bb80","entry":"normalize_matrices","repo":"robertsi20/Conceptualizing-Uncertainty","repo_kind":"listed","path":"concept_helpers/disc_nmf.py","file_url":"https://github.com/robertsi20/Conceptualizing-Uncertainty/blob/HEAD/concept_helpers/disc_nmf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"832caef4ff71bb80"}},{"code_sha256_prefix":"1e531fa3df0ff008","entry":"predict_with_uncertainty_batched","repo":"robertsi20/Conceptualizing-Uncertainty","repo_kind":"listed","path":"experiment_helpers/.ipynb_checkpoints/experiment_helper_functions-checkpoint.py","file_url":"https://github.com/robertsi20/Conceptualizing-Uncertainty/blob/HEAD/experiment_helpers/.ipynb_checkpoints/experiment_helper_functions-checkpoint.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e531fa3df0ff008"}},{"code_sha256_prefix":"9e910a1703b00aee","entry":"preprocess_images_in_batches","repo":"robertsi20/Conceptualizing-Uncertainty","repo_kind":"listed","path":"experiment_helpers/.ipynb_checkpoints/experiment_helper_functions-checkpoint.py","file_url":"https://github.com/robertsi20/Conceptualizing-Uncertainty/blob/HEAD/experiment_helpers/.ipynb_checkpoints/experiment_helper_functions-checkpoint.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e910a1703b00aee"}},{"code_sha256_prefix":"e13469045ccef417","entry":"prob_neg","repo":"robertsi20/Conceptualizing-Uncertainty","repo_kind":"listed","path":"Uncertainty_Functions/unc_functions.py","file_url":"https://github.com/robertsi20/Conceptualizing-Uncertainty/blob/HEAD/Uncertainty_Functions/unc_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e13469045ccef417"}},{"code_sha256_prefix":"24a16cd8049665b6","entry":"prob_pos","repo":"robertsi20/Conceptualizing-Uncertainty","repo_kind":"listed","path":"Uncertainty_Functions/unc_functions.py","file_url":"https://github.com/robertsi20/Conceptualizing-Uncertainty/blob/HEAD/Uncertainty_Functions/unc_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"24a16cd8049665b6"}},{"code_sha256_prefix":"f9ffd38002957cca","entry":"uncertainty_matrices","repo":"robertsi20/Conceptualizing-Uncertainty","repo_kind":"listed","path":"experiment_helpers/lm_experiment_helper_functions.py","file_url":"https://github.com/robertsi20/Conceptualizing-Uncertainty/blob/HEAD/experiment_helpers/lm_experiment_helper_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9ffd38002957cca"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}