{"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/long-tailed-out-of-distribution-detection","title":"Long-Tailed Out-of-Distribution Detection: Prioritizing Attention to Tail","arxiv_id":"2408.06742","date":"2024-08-13","proceeding":null,"authors":["Yina He","Lei Peng","Yongcun Zhang","Juanjuan Weng","Zhiming Luo","Shaozi Li"],"abstract":"Current out-of-distribution (OOD) detection methods typically assume balanced in-distribution (ID) data, while most real-world data follow a long-tailed distribution. Previous approaches to long-tailed OOD detection often involve balancing the ID data by reducing the semantics of head classes. However, this reduction can severely affect the classification accuracy of ID data. The main challenge of this task lies in the severe lack of features for tail classes, leading to confusion with OOD data. To tackle this issue, we introduce a novel Prioritizing Attention to Tail (PATT) method using augmentation instead of reduction. Our main intuition involves using a mixture of von Mises-Fisher (vMF) distributions to model the ID data and a temperature scaling module to boost the confidence of ID data. This enables us to generate infinite contrastive pairs, implicitly enhancing the semantics of ID classes while promoting differentiation between ID and OOD data. To further strengthen the detection of OOD data without compromising the classification performance of ID data, we propose feature calibration during the inference phase. By extracting an attention weight from the training set that prioritizes the tail classes and reduces the confidence in OOD data, we improve the OOD detection capability. Extensive experiments verified that our method outperforms the current state-of-the-art methods on various benchmarks.","url_abs":"https://arxiv.org/abs/2408.06742v3","url_pdf":"https://arxiv.org/pdf/2408.06742v3.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":"long-tailed-out-of-distribution-detection","repo_url":"https://github.com/inar-design/patt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2408.06742","atlas_url":"https://app.syntology.ai/?focus=2408.06742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06742"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/inar-design/patt","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":"c1c5637c9970cab6","entry":"ResNet18","repo":"inar-design/patt","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/inar-design/patt/blob/HEAD/models/resnet.py","link_basis":"first_harvest_node","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":"c1c5637c9970cab6"}},{"code_sha256_prefix":"8de82e83c702450c","entry":"ResNet34","repo":"inar-design/patt","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/inar-design/patt/blob/HEAD/models/resnet.py","link_basis":"first_harvest_node","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":"8de82e83c702450c"}},{"code_sha256_prefix":"07c04376ec2f148f","entry":"ResNet50","repo":"inar-design/patt","repo_kind":"official","path":"models/resnet_imagenet.py","file_url":"https://github.com/inar-design/patt/blob/HEAD/models/resnet_imagenet.py","link_basis":"first_harvest_node","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":"07c04376ec2f148f"}},{"code_sha256_prefix":"87171ac55803dbfd","entry":"miller_recurrence","repo":"inar-design/patt","repo_kind":"official","path":"loss/proco.py","file_url":"https://github.com/inar-design/patt/blob/HEAD/loss/proco.py","link_basis":"first_harvest_node","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":"87171ac55803dbfd"}},{"code_sha256_prefix":"0ddb7c161e4f4ff3","entry":"tinyimages300k_dataloaders","repo":"inar-design/patt","repo_kind":"official","path":"dataset/tinyimages_300k.py","file_url":"https://github.com/inar-design/patt/blob/HEAD/dataset/tinyimages_300k.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0ddb7c161e4f4ff3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}