{"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/augmenting-softmax-information-for-selective","title":"Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data","arxiv_id":"2207.07506","date":"2022-07-15","proceeding":null,"authors":["Guoxuan Xia","Christos-Savvas Bouganis"],"abstract":"Detecting out-of-distribution (OOD) data is a task that is receiving an increasing amount of research attention in the domain of deep learning for computer vision. However, the performance of detection methods is generally evaluated on the task in isolation, rather than also considering potential downstream tasks in tandem. In this work, we examine selective classification in the presence of OOD data (SCOD). That is to say, the motivation for detecting OOD samples is to reject them so their impact on the quality of predictions is reduced. We show under this task specification, that existing post-hoc methods perform quite differently compared to when evaluated only on OOD detection. This is because it is no longer an issue to conflate in-distribution (ID) data with OOD data if the ID data is going to be misclassified. However, the conflation within ID data of correct and incorrect predictions becomes undesirable. We also propose a novel method for SCOD, Softmax Information Retaining Combination (SIRC), that augments softmax-based confidence scores with feature-agnostic information such that their ability to identify OOD samples is improved without sacrificing separation between correct and incorrect ID predictions. Experiments on a wide variety of ImageNet-scale datasets and convolutional neural network architectures show that SIRC is able to consistently match or outperform the baseline for SCOD, whilst existing OOD detection methods fail to do so.","url_abs":"https://arxiv.org/abs/2207.07506v3","url_pdf":"https://arxiv.org/pdf/2207.07506v3.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":"augmenting-softmax-information-for-selective","repo_url":"https://github.com/guoxoug/sirc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"ood-detection","task_name":"Out of Distribution (OOD) Detection"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.07506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07506"}},"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/guoxoug/sirc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"unverified":4},"by_repo_kind":{"official":{"samples":8,"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":"d9def42110729a85","entry":"conv1x1","repo":"guoxoug/sirc","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/guoxoug/sirc/blob/HEAD/models/resnet.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"ee80cf467065076b","entry":"conv1x1","repo":"guoxoug/sirc","repo_kind":"official","path":"models/resnet_v2.py","file_url":"https://github.com/guoxoug/sirc/blob/HEAD/models/resnet_v2.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee80cf467065076b"}},{"code_sha256_prefix":"600ff2c45e0de056","entry":"conv3x3","repo":"guoxoug/sirc","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/guoxoug/sirc/blob/HEAD/models/resnet.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"600ff2c45e0de056"}},{"code_sha256_prefix":"f01b8d3901f0b289","entry":"conv3x3","repo":"guoxoug/sirc","repo_kind":"official","path":"models/resnet_v2.py","file_url":"https://github.com/guoxoug/sirc/blob/HEAD/models/resnet_v2.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f01b8d3901f0b289"}},{"code_sha256_prefix":"103cc888080a8049","entry":"clean_strings","repo":"guoxoug/sirc","repo_kind":"official","path":"plot_ood_sc_comp.py","file_url":"https://github.com/guoxoug/sirc/blob/HEAD/plot_ood_sc_comp.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":"103cc888080a8049"}},{"code_sha256_prefix":"8440a5f6d860790e","entry":"get_valid_invalid_split","repo":"guoxoug/sirc","repo_kind":"official","path":"plot_vary_sc_params.py","file_url":"https://github.com/guoxoug/sirc/blob/HEAD/plot_vary_sc_params.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":"8440a5f6d860790e"}},{"code_sha256_prefix":"527c3342c6b829a2","entry":"risk_coverage_curve","repo":"guoxoug/sirc","repo_kind":"official","path":"plot_vary_sc_params.py","file_url":"https://github.com/guoxoug/sirc/blob/HEAD/plot_vary_sc_params.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":"527c3342c6b829a2"}},{"code_sha256_prefix":"e875479ad6ebfc7a","entry":"tf2th","repo":"guoxoug/sirc","repo_kind":"official","path":"models/resnet_v2.py","file_url":"https://github.com/guoxoug/sirc/blob/HEAD/models/resnet_v2.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":"e875479ad6ebfc7a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}