{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:35:36Z","timestamp":1787013336365,"version":"build-2736575974"},"reference-count":96,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"European Union&#x0027;s Horizon Europe research and innovation program","award":["101120237"],"award-info":[{"award-number":["101120237"]}]},{"name":"PNRR project FAIR - Future AI Research","award":["PE00000013"],"award-info":[{"award-number":["PE00000013"]}]},{"name":"NRRP MUR program"},{"DOI":"10.13039\/100031478","name":"NextGenerationEU","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100031478","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2022XKRC015"],"award-info":[{"award-number":["2022XKRC015"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National NSF of China","award":["62372033"],"award-info":[{"award-number":["62372033"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tpami.2024.3520899","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T14:16:51Z","timestamp":1734963411000},"page":"2505-2519","source":"Crossref","is-referenced-by-count":6,"title":["RankFeat&amp;RankWeight: Rank-1 Feature\/Weight Removal for Out-of-Distribution Detection"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1573-5643","authenticated-orcid":false,"given":"Yue","family":"Song","sequence":"first","affiliation":[{"name":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5477-1017","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6597-7248","authenticated-orcid":false,"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"ref2","first-page":"29074","article-title":"Can multi-label classification networks know what they don\u2019t know?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref3","first-page":"677","article-title":"On the importance of gradients for detecting distributional shifts in the wild","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref4","first-page":"1179","article-title":"Single layer predictive normalized maximum likelihood for out-of-distribution detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bibas"},{"key":"ref5","first-page":"664","article-title":"A winning hand: Compressing deep networks can improve out-of-distribution robustness","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Diffenderfer"},{"key":"ref6","first-page":"144","article-title":"ReAct: Out-of-distribution detection with rectified activations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref7","first-page":"1660","article-title":"Adaptive conformal inference under distribution shift","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gibbs"},{"key":"ref8","first-page":"7068","article-title":"Exploring the limits of out-of-distribution detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fort"},{"key":"ref9","first-page":"29754","article-title":"Robust generalization despite distribution shift via minimum discriminating information","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sutter"},{"key":"ref10","first-page":"23519","article-title":"Towards a theoretical framework of out-of-distribution generalization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ye"},{"key":"ref11","article-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kumar"},{"key":"ref12","article-title":"Leveraging unlabeled data to predict out-of-distribution performance","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Garg"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00933"},{"key":"ref14","article-title":"VOS: Learning what you don\u2019t know by virtual outlier synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Du"},{"key":"ref15","article-title":"IGEOOD: An information geometry approach to out-of-distribution detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gomes"},{"key":"ref16","article-title":"A statistical framework for efficient out of distribution detection in deep neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Haroush"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00487"},{"key":"ref18","article-title":"Extremely simple activation shaping for out-of-distribution detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Djurisic"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_40"},{"key":"ref20","article-title":"OpenOOD v1.5: Enhanced benchmark for out-of-distribution detection","author":"Zhang","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00162"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00150"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01780"},{"key":"ref24","first-page":"7167","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","article-title":"VRA: Variational rectified activation for out-of-distribution detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref27","first-page":"21 464","article-title":"Energy-based out-of-distribution detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref28","article-title":"RankFeat: Rank-1 feature removal for out-of-distribution detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1214\/088342306000000060"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262170055.001.0001"},{"key":"ref31","first-page":"5637","article-title":"WILDS: A benchmark of in-the-wild distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"key":"ref32","article-title":"A fine-grained analysis on distribution shift","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wiles"},{"key":"ref33","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks"},{"key":"ref34","article-title":"Can you trust your model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ovadia"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01096"},{"key":"ref36","first-page":"9229","article-title":"Test-time training with self-supervision for generalization under distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref37","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks"},{"key":"ref38","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00849"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01072"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.256"},{"key":"ref42","article-title":"Open-set recognition: A good closed-set classifier is all you need","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Vaze"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00057"},{"key":"ref44","first-page":"11 839","article-title":"CSI: Novelty detection via contrastive learning on distributionally shifted instances","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tack"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1970.1054406"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45665-1_6"},{"key":"ref47","article-title":"Training confidence-calibrated classifiers for detecting out-of-distribution samples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref48","first-page":"7047","article-title":"Predictive uncertainty estimation via prior networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Malinin"},{"key":"ref49","first-page":"2151","article-title":"SelectiveNet: A deep neural network with an integrated reject option","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Geifman"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00013"},{"key":"ref51","article-title":"Towards neural networks that provably know when they don\u2019t know","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meinke"},{"key":"ref52","article-title":"OOD-MAML: Meta-learning for few-shot out-of-distribution detection and classification","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jeong"},{"key":"ref53","article-title":"Uncertainty estimation using a single deep deterministic neural network","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Van Amersfoort"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00819"},{"key":"ref55","first-page":"23631","article-title":"Mitigating neural network overconfidence with logit normalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wei"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01331"},{"key":"ref57","first-page":"10848","article-title":"Training OOD detectors in their natural habitats","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katz-Samuels"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02117-4"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.173"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00860"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2861839"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3004398"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3024728"},{"key":"ref64","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.21423"},{"key":"ref66","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rezende"},{"key":"ref67","first-page":"4790","article-title":"Conditional image generation with PixelCNN decoders","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Van den Oord"},{"key":"ref68","article-title":"Density estimation using real NVP","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dinh"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.202"},{"key":"ref70","article-title":"Revisiting flow generative models for out-of-distribution detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jiang"},{"key":"ref71","first-page":"14680","article-title":"Likelihood ratios for out-of-distribution detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref72","article-title":"Input complexity and out-of-distribution detection with likelihood-based generative models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Serr\u00e0"},{"key":"ref73","first-page":"8982","article-title":"Further analysis of outlier detection with deep generative models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref74","first-page":"20 685","article-title":"Likelihood regret: An out-of-distribution detection score for variational auto-encoder","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xiao"},{"key":"ref75","first-page":"20 578","article-title":"Why normalizing flows fail to detect out-of-distribution data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kirichenko"},{"key":"ref76","first-page":"21 038","article-title":"Understanding anomaly detection with deep invertible networks through hierarchies of distributions and features","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Schirrmeister"},{"key":"ref77","first-page":"14913","article-title":"Locally most powerful Bayesian test for out-of-distribution detection using deep generative models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref78","article-title":"Non-parametric outlier synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tao"},{"key":"ref79","article-title":"Dream the impossible: Outlier imagination with diffusion models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Du"},{"key":"ref80","article-title":"Do deep generative models know what they don\u2019t know?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nalisnick"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1070\/SM1967v001n04ABEH001994"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.60.3389"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref85","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks"},{"key":"ref86","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and $< $< 0.5 MB model size","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Iandola","year":"2017"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref88","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref90","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref95","first-page":"8759","article-title":"Scaling out-of-distribution detection for real-world settings","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hendrycks"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_29"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10916529\/10812065.pdf?arnumber=10812065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T15:41:40Z","timestamp":1743781300000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10812065\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":96,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3520899","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}