{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:06:53Z","timestamp":1777889213038,"version":"3.51.4"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010663","name":"European Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009129","name":"SR","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00335","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3509-3519","source":"Crossref","is-referenced-by-count":0,"title":["Activation Subspaces for Out-of-Distribution Detection"],"prefix":"10.1109","author":[{"given":"Bar\u0131\u015f","family":"Z\u00f6ng\u00fcr","sequence":"first","affiliation":[{"name":"TU Darmstadt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robin","family":"Hesse","sequence":"additional","affiliation":[{"name":"TU Darmstadt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Roth","sequence":"additional","affiliation":[{"name":"TU Darmstadt"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01901"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1659"},{"key":"ref3","first-page":"2471","article-title":"In or out? Fixing ImageNet out-of-distribution detection evaluation","author":"Bitterwolf","year":"2023","journal-title":"ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19894"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00508"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3501"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref8","author":"Cook","year":"2007","journal-title":"Outlier detection through null space analysis of neural networks"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"309","key":"ref10","first-page":"1","article-title":"The separation capacity of random neural networks","author":"Dirksen","year":"2022","journal-title":"Int. J. Comput. Vision"},{"key":"ref11","article-title":"Extremely simple activation shaping for out-of-distribution detection","author":"Djurisic","year":"2023","journal-title":"ICLR"},{"key":"ref12","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4268"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1131"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01780"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"Hendrycks","year":"2017","journal-title":"ICLR"},{"key":"ref18","article-title":"Dietterich","author":"Hendrycks","year":"2019","journal-title":"Deep anomaly detection with outlier exposure. In ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref20","first-page":"8759","article-title":"Scaling out-of-distribution detection for real-world settings","author":"Hendrycks","year":"2022","journal-title":"ICML"},{"key":"ref21","article-title":"Energy-based Hopfield boosting for out-of-distribution detection","author":"Hofmann","year":"2024","journal-title":"NeurIPS"},{"key":"ref22","first-page":"8769","article-title":"Belongie","author":"Van Horn","year":"2018","journal-title":"The iNaturalist species classification and detection dataset. In CVPR"},{"key":"ref23","first-page":"770","article-title":"Weinberger","author":"Huang","year":"2017","journal-title":"Densely connected convolutional networks. In CVPR"},{"key":"ref24","first-page":"8710","article-title":"MOS: Towards scaling out-ofdistribution detection for large semantic space","author":"Huang","year":"2021","journal-title":"CVPR"},{"key":"ref25","first-page":"677","article-title":"On the importance of gradients for detecting distributional shifts in the wild","author":"Huang","year":"2021","journal-title":"NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167"},{"key":"ref27","article-title":"Directional convergence and alignment in deep learning","author":"Ji","year":"2020","journal-title":"NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2307\/2325085"},{"key":"ref29","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009","journal-title":"Technical report, University of Toronto"},{"key":"ref30","author":"LeCun","year":"2010","journal-title":"MNIST handwritten digit database"},{"key":"ref31","first-page":"71677177","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","author":"Lee","year":"2018","journal-title":"NeurIPS"},{"key":"ref32","article-title":"SeTAR: Out-of-distribution detection with selective low-rank approximation","author":"Li","year":"2024","journal-title":"NeurIPS"},{"key":"ref33","article-title":"Srikant","author":"Liang","year":"2018","journal-title":"Enhancing the reliability of out-of-distribution image detection in neural networks. In ICLR"},{"key":"ref34","first-page":"1531315323","article-title":"MOOD: Multilevel out-of-distribution detection","author":"Lin","year":"2021","journal-title":"CVPR"},{"key":"ref35","article-title":"Fast decision boundary based out-of-distribution detector","author":"Liu","year":"2024","journal-title":"ICML"},{"key":"ref36","article-title":"Energy-based out-of-distribution detection","author":"Liu","year":"2020","journal-title":"In NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02293"},{"key":"ref38","article-title":"Learning with mixture of prototypes for out-of-distribution detection","author":"Lu","year":"2024","journal-title":"ICLR"},{"key":"ref39","author":"Ming","year":"2023","journal-title":"How to exploit hyperspherical embeddings for out-of-distribution detection? In ICLR"},{"key":"ref40","author":"Netzer","year":"2011","journal-title":"Reading digits in natural images with unsupervised feature learning"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00162"},{"key":"ref42","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"In NeurIPS"},{"key":"ref43","author":"Ren","year":"2021","journal-title":"A simple fix to Mahalanobis distance for improving near-OOD detection"},{"issue":"3","key":"ref44","first-page":"211","volume":"115","author":"Russakovsky","year":"2015","journal-title":"ImageNet large scale visual recognition challenge. Int. J. Comput. Vision"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref46","article-title":"SSD: A unified framework for self-supervised outlier detection","author":"Sehwag","year":"2021","journal-title":"ICLR"},{"key":"ref47","first-page":"307318","article-title":"17","author":"Shapley","year":"1953","journal-title":"A Value for n-Person Games"},{"key":"ref48","article-title":"RankFeat: Rank-1 feature removal for out-of-distribution detection","author":"Song","year":"2022","journal-title":"NeurIPS"},{"key":"ref49","author":"Strang","year":"2006","journal-title":"Linear Algebra and Its Applications. Thomson, Brooks\/Cole"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_40"},{"key":"ref51","article-title":"ReAct: Out-ofdistribution detection with rectified activations","author":"Sun","year":"2021","journal-title":"NeurIPS"},{"key":"ref52","first-page":"20827","article-title":"Out-ofdistribution detection with deep nearest neighbors","author":"Sun","year":"2022","journal-title":"ICML"},{"key":"ref53","first-page":"9446","article-title":"Lempitsky","author":"Ulyanov","year":"2018","journal-title":"Deep image prior. In CVPR"},{"key":"ref54","article-title":"Open-set recognition: A good closed-set classifier is all you need","author":"Vaze","year":"2022","journal-title":"ICLR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00487"},{"key":"ref56","first-page":"3485","article-title":"Ehinger, Aude Oliva, and Antonio Torralba","author":"Xiao","year":"2010","journal-title":"SUN database: Large-scale scene recognition from abbey to zoo. In CVPR"},{"key":"ref57","article-title":"Scaling for training time and post-hoc out-of-distribution detection enhancement","author":"Xu","year":"2024","journal-title":"ICLR"},{"key":"ref58","article-title":"VRA: Variational rectified activation for out-of-distribution detection","author":"Xu","year":"2023","journal-title":"NeurIPS"},{"key":"ref59","author":"Xu","year":"2015","journal-title":"TurkerGaze: Crowdsourcing saliency with webcam based eye tracking"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02117-4"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02473"},{"key":"ref62","article-title":"Out-of-distribution detection based on in-distribution data patterns memorization with modern Hopfield energy","author":"Zhang","year":"2023","journal-title":"ICLR"},{"key":"ref63","author":"Zhang","year":"2023","journal-title":"OpenOOD v1.5: Enhanced benchmark for out-of-distribution detection"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00330"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref66","article-title":"Boosting out-of-distribution detection with typical features","author":"Zhu","year":"2022","journal-title":"NeurIPS"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444245.pdf?arnumber=11444245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:09:01Z","timestamp":1777612141000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444245\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00335","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}