{"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/revisiting-deep-ensemble-for-out-of","title":"Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspective","arxiv_id":"2310.14227","date":"2023-10-22","proceeding":null,"authors":["Kun Fang","Qinghua Tao","Xiaolin Huang","Jie Yang"],"abstract":"Existing Out-of-Distribution (OoD) detection methods address to detect OoD samples from In-Distribution (InD) data mainly by exploring differences in features, logits and gradients in Deep Neural Networks (DNNs). We in this work propose a new perspective upon loss landscape and mode ensemble to investigate OoD detection. In the optimization of DNNs, there exist many local optima in the parameter space, or namely modes. Interestingly, we observe that these independent modes, which all reach low-loss regions with InD data (training and test data), yet yield significantly different loss landscapes with OoD data. Such an observation provides a novel view to investigate the OoD detection from the loss landscape, and further suggests significantly fluctuating OoD detection performance across these modes. For instance, FPR values of the RankFeat method can range from 46.58% to 84.70% among 5 modes, showing uncertain detection performance evaluations across independent modes. Motivated by such diversities on OoD loss landscape across modes, we revisit the deep ensemble method for OoD detection through mode ensemble, leading to improved performance and benefiting the OoD detector with reduced variances. Extensive experiments covering varied OoD detectors and network structures illustrate high variances across modes and validate the superiority of mode ensemble in boosting OoD detection. We hope this work could attract attention in the view of independent modes in the loss landscape of OoD data and more reliable evaluations on OoD detectors.","url_abs":"https://arxiv.org/abs/2310.14227v2","url_pdf":"https://arxiv.org/pdf/2310.14227v2.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":"revisiting-deep-ensemble-for-out-of","repo_url":"https://github.com/fanghenshaometeor/ood-mode-ensemble","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":{"atlas_url":"https://app.syntology.ai/?focus=2310.14227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14227"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fanghenshaometeor/ood-mode-ensemble","reach":{"status":"ok"}}],"summary":{"ran_fixture":2,"ran_draft_wrong":1,"ran_honours":1,"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":7,"samples":[{"code_sha256_prefix":"131a82fd65128218","entry":"accuracy","repo":"fanghenshaometeor/ood-mode-ensemble","repo_kind":"official","path":"train_imgnet.py","file_url":"https://github.com/fanghenshaometeor/ood-mode-ensemble/blob/HEAD/train_imgnet.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"131a82fd65128218"}},{"code_sha256_prefix":"00e569acd6b45ef0","entry":"conv3x3","repo":"fanghenshaometeor/ood-mode-ensemble","repo_kind":"official","path":"model/cifar_wrn.py","file_url":"https://github.com/fanghenshaometeor/ood-mode-ensemble/blob/HEAD/model/cifar_wrn.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"00e569acd6b45ef0"}},{"code_sha256_prefix":"e1dfe697d81dc165","entry":"fpr_and_fdr_at_recall","repo":"fanghenshaometeor/ood-mode-ensemble","repo_kind":"official","path":"utils_ood.py","file_url":"https://github.com/fanghenshaometeor/ood-mode-ensemble/blob/HEAD/utils_ood.py","link_basis":"harvester_set","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":"e1dfe697d81dc165"}},{"code_sha256_prefix":"d4acb3120a027622","entry":"stable_cumsum","repo":"fanghenshaometeor/ood-mode-ensemble","repo_kind":"official","path":"utils_ood.py","file_url":"https://github.com/fanghenshaometeor/ood-mode-ensemble/blob/HEAD/utils_ood.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d4acb3120a027622"}},{"code_sha256_prefix":"1cbfd457cc77abb8","entry":"validate","repo":"fanghenshaometeor/ood-mode-ensemble","repo_kind":"official","path":"train_imgnet.py","file_url":"https://github.com/fanghenshaometeor/ood-mode-ensemble/blob/HEAD/train_imgnet.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":"1cbfd457cc77abb8"}},{"code_sha256_prefix":"6ae97a54ffd19675","entry":"densenet121","repo":"fanghenshaometeor/ood-mode-ensemble","repo_kind":"official","path":"model/imgnet_densenet.py","file_url":"https://github.com/fanghenshaometeor/ood-mode-ensemble/blob/HEAD/model/imgnet_densenet.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":"6ae97a54ffd19675"}},{"code_sha256_prefix":"97bd984c2845caec","entry":"make_id_ood","repo":"fanghenshaometeor/ood-mode-ensemble","repo_kind":"official","path":"utils_ood.py","file_url":"https://github.com/fanghenshaometeor/ood-mode-ensemble/blob/HEAD/utils_ood.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":"97bd984c2845caec"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}