{"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/boosting-out-of-distribution-detection-with-1","title":"Boosting Out-of-Distribution Detection with Multiple Pre-trained Models","arxiv_id":"2212.12720","date":"2022-12-24","proceeding":null,"authors":["Feng Xue","Zi He","Chuanlong Xie","Falong Tan","Zhenguo Li"],"abstract":"Out-of-Distribution (OOD) detection, i.e., identifying whether an input is sampled from a novel distribution other than the training distribution, is a critical task for safely deploying machine learning systems in the open world. Recently, post hoc detection utilizing pre-trained models has shown promising performance and can be scaled to large-scale problems. This advance raises a natural question: Can we leverage the diversity of multiple pre-trained models to improve the performance of post hoc detection methods? In this work, we propose a detection enhancement method by ensembling multiple detection decisions derived from a zoo of pre-trained models. Our approach uses the p-value instead of the commonly used hard threshold and leverages a fundamental framework of multiple hypothesis testing to control the true positive rate of In-Distribution (ID) data. We focus on the usage of model zoos and provide systematic empirical comparisons with current state-of-the-art methods on various OOD detection benchmarks. The proposed ensemble scheme shows consistent improvement compared to single-model detectors and significantly outperforms the current competitive methods. Our method substantially improves the relative performance by 65.40% and 26.96% on the CIFAR10 and ImageNet benchmarks.","url_abs":"https://arxiv.org/abs/2212.12720v2","url_pdf":"https://arxiv.org/pdf/2212.12720v2.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":"boosting-out-of-distribution-detection-with-1","repo_url":"https://github.com/mapleleaf6/zode","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"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":"deep-ensembles","method_name":"Deep Ensembles"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/out-of-distribution-detection-on-cifar-10","task":"Out-of-Distribution Detection","dataset":"CIFAR-10","model":"ZODE-KNN","rank_in_archive_order":6,"of":10,"metrics":{"AUROC":"99.12","FPR95":"3.83"},"uses_additional_data":false},{"leaderboard":"/sota/out-of-distribution-detection-on-cifar-10-vs","task":"Out-of-Distribution Detection","dataset":"CIFAR-10 vs CIFAR-100","model":"ZODE-KNN","rank_in_archive_order":6,"of":14,"metrics":{"AUROC":"97.12","FPR95":"18.29"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.12720","atlas_url":"https://app.syntology.ai/?focus=2212.12720","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}