{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:21:22Z","timestamp":1777890082859,"version":"3.51.4"},"reference-count":49,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00179","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1836-1845","source":"Crossref","is-referenced-by-count":0,"title":["Diagnosing Pretrained Models for Out-of-Distribution Detection"],"prefix":"10.1109","author":[{"given":"Haipeng","family":"Xiong","sequence":"first","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Xu","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Angela","family":"Yao","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"In or out? Fixing ImageNet out-of-distribution detection evaluation","author":"Bitterwolf","year":"2023","journal-title":"ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref5","article-title":"Extremely simple activation shaping for out-ofdistribution detection","author":"Djurisic","year":"2023","journal-title":"ICLR"},{"key":"ref6","article-title":"Towards unknown-aware learning with virtual outlier synthesis","volume-title":"International Conference on Learning Representations","author":"Du","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.10.010"},{"key":"ref8","article-title":"Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness","author":"Geirhos","year":"2018","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i18.29961"},{"key":"ref10","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings","author":"Hendrycks","year":"2017"},{"key":"ref11","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","volume-title":"International Conference on Learning Representations","author":"Hendrycks","year":"2017"},{"key":"ref12","article-title":"Deep anomaly detection with outlier exposure","volume-title":"7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6\u20139, 2019","author":"Hendrycks","year":"2019"},{"key":"ref13","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","author":"Hendrycks","year":"2020","journal-title":"ICLR"},{"key":"ref14","article-title":"Augmix: A simple method to improve robustness and uncertainty under data shift","volume-title":"International Conference on Learning Representations","author":"Hendrycks","year":"2020"},{"key":"ref15","article-title":"Scaling out-of-distribution detection for real-world settings","author":"Hendrycks","year":"2022","journal-title":"ICML"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00860"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02135"},{"key":"ref19","first-page":"876","article-title":"Averaging weights leads to wider optima and better generalization","author":"Izmailov","year":"2018","journal-title":"Uncertainty in Artificial Intelligence"},{"key":"ref20","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"issue":"7","key":"ref21","first-page":"3","article-title":"Tiny imagenet visual recognition challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS 231N"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref23","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","author":"Lee","year":"2018","journal-title":"NeurIPS"},{"key":"ref24","article-title":"Energy-based out-of-distribution detection","author":"Liu","year":"2020","journal-title":"NeurIPS"},{"key":"ref25","article-title":"Recent advances in ood detection: Problems and approaches","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"How to exploit hyperspherical embeddings for out-of-distribution detection?","volume-title":"The Eleventh International Conference on Learning Representations","author":"Ming","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00081"},{"key":"ref28","article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"NIPS Workshop","author":"Netzer","year":"2011"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00162"},{"key":"ref30","article-title":"Using mixup as a regularizer can surprisingly improve accuracy & out-of-distribution robustness","author":"Pinto","year":"2022","journal-title":"NeurIPS"},{"key":"ref31","article-title":"T2fnorm: Extremely simple scaled train-time feature normalization for ood detection","author":"Regmi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"ReAct: Out-ofdistribution detection with rectified activations","author":"Sun","year":"2021","journal-title":"NeurIPS"},{"key":"ref33","first-page":"20827","article-title":"Out-of-distribution detection with deep nearest neighbors","volume-title":"International Conference on Machine Learning","author":"Sun","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref35","article-title":"Nonparametric outlier synthesis","volume-title":"The Eleventh International Conference on Learning Representations","author":"Tao","year":"2023"},{"key":"ref36","volume-title":"How to train state-of-the-art models using torchvision latest primitives","year":"2024"},{"key":"ref37","article-title":"Open-set recognition: A good closed-set classifier is all you need","author":"Vaze","year":"2022","journal-title":"ICLR"},{"key":"ref38","article-title":"Open-set recognition: A good closed-set classifier is all you need","volume-title":"International Conference on Learning Representations","author":"Vaze","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00487"},{"key":"ref40","article-title":"Mitigating neural network overconfidence with logit normalization","author":"Wei","year":"2022","journal-title":"ICML"},{"key":"ref41","article-title":"Understanding why label smoothing degrades selective classification and how to fix it","author":"Xia","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"OpenOOD: Benchmarking generalized out-of-distribution detection","author":"Yang","year":"2022","journal-title":"NeurIPS"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref45","author":"Zhang","year":"2023","journal-title":"OpenOOD v1.5: Enhanced benchmark for out-of-distribution detection"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3342285"},{"key":"ref49","first-page":"2597","article-title":"Mixupe: Understanding and improving mixup from directional derivative perspective","volume-title":"Uncertainty in Artificial Intelligence","author":"Zou","year":"2023"}],"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\/11444043.pdf?arnumber=11444043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:56Z","timestamp":1777613336000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444043\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00179","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}