{"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/neuron-activation-coverage-rethinking-out-of","title":"Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization","arxiv_id":"2306.02879","date":"2023-06-05","proceeding":null,"authors":["Yibing Liu","Chris Xing Tian","Haoliang Li","Lei Ma","Shiqi Wang"],"abstract":"The out-of-distribution (OOD) problem generally arises when neural networks encounter data that significantly deviates from the training data distribution, i.e., in-distribution (InD). In this paper, we study the OOD problem from a neuron activation view. We first formulate neuron activation states by considering both the neuron output and its influence on model decisions. Then, to characterize the relationship between neurons and OOD issues, we introduce the \\textit{neuron activation coverage} (NAC) -- a simple measure for neuron behaviors under InD data. Leveraging our NAC, we show that 1) InD and OOD inputs can be largely separated based on the neuron behavior, which significantly eases the OOD detection problem and beats the 21 previous methods over three benchmarks (CIFAR-10, CIFAR-100, and ImageNet-1K). 2) a positive correlation between NAC and model generalization ability consistently holds across architectures and datasets, which enables a NAC-based criterion for evaluating model robustness. Compared to prevalent InD validation criteria, we show that NAC not only can select more robust models, but also has a stronger correlation with OOD test performance.","url_abs":"https://arxiv.org/abs/2306.02879v3","url_pdf":"https://arxiv.org/pdf/2306.02879v3.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":"neuron-activation-coverage-rethinking-out-of","repo_url":"https://github.com/bierone/ood_coverage","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"out-of-distribution-detection","task_name":"Out-of-Distribution Detection"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-11","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs OpenImage-O","model":"NAC-UE (ResNet-50)","rank_in_archive_order":6,"of":7,"metrics":{"AUROC":"91.45"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-10","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs Textures","model":"NAC-UE (ResNet-50)","rank_in_archive_order":3,"of":34,"metrics":{"AUROC":"97.9"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-imagenet-1k-3","task":"Out-of-Distribution Detection","dataset":"ImageNet-1k vs iNaturalist","model":"NAC-UE (ResNet-50)","rank_in_archive_order":12,"of":28,"metrics":{"AUROC":"96.52"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.02879","atlas_url":"https://app.syntology.ai/?focus=2306.02879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02879"}},"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/BierOne/ood","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bierone/ood_coverage","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":"b6dc3c09cf446d1d","entry":"Coverage","repo":"bierone/ood_coverage","repo_kind":"official","path":"openood/postprocessors/nac/coverage.py","file_url":"https://github.com/bierone/ood_coverage/blob/HEAD/openood/postprocessors/nac/coverage.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":"b6dc3c09cf446d1d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}