{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T20:45:24Z","timestamp":1777322724236,"version":"3.51.4"},"reference-count":99,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"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"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372033"],"award-info":[{"award-number":["62372033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Beijing Municipality","award":["L252025"],"award-info":[{"award-number":["L252025"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3679195","type":"journal-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T19:49:06Z","timestamp":1775764146000},"page":"4064-4077","source":"Crossref","is-referenced-by-count":0,"title":["Sharpness-Aware Fine-Tuning for OOD Detection"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6256-3831","authenticated-orcid":false,"given":"Chi","family":"Zhang","sequence":"first","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5477-1017","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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 (DISI), University of Trento, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1573-5643","authenticated-orcid":false,"given":"Yue","family":"Song","sequence":"additional","affiliation":[{"name":"College of AI, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Open-set recognition: A good closed-set classifier is all you need?","author":"Vaze","year":"2021","journal-title":"arXiv:2110.06207"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1300"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"ref4","first-page":"7167","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume-title":"Proc. NeurIPS","author":"Lee"},{"key":"ref5","first-page":"677","article-title":"On the importance of gradients for detecting distributional shifts in the wild","volume-title":"Proc. NeurIPS","volume":"34","author":"Huang"},{"key":"ref6","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume-title":"Proc. NeurIPS","volume":"33","author":"Liu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00860"},{"key":"ref8","first-page":"8759","article-title":"Scaling out-of-distribution detection for real-world settings","volume-title":"Proc. ICML","author":"Hendrycks"},{"key":"ref9","article-title":"Deep anomaly detection with outlier exposure","author":"Hendrycks","year":"2018","journal-title":"arXiv:1812.04606"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01507"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2660"},{"key":"ref12","article-title":"Sharpness-aware minimization for efficiently improving generalization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Foret"},{"key":"ref13","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","volume-title":"Proc. ICLR","author":"Hendrycks"},{"key":"ref14","article-title":"Extremely simple activation shaping for out-of-distribution detection","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Djurisic"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1260"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.508"},{"key":"ref17","article-title":"When vision transformers outperform resnets without pre-training or strong data augmentations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref18","first-page":"5905","article-title":"ASAM: Adaptive sharpness-aware minimization for scale-invariant learning of deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kwon"},{"key":"ref19","article-title":"Surrogate gap minimization improves sharpness-aware training","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhuang"},{"key":"ref20","article-title":"Normalization layers are all that sharpness-aware minimization needs","author":"Mueller","year":"2023","journal-title":"arXiv:2306.04226"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2244"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01204"},{"key":"ref23","article-title":"Efficient sharpness-aware minimization for improved training of neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Du"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2037"},{"key":"ref25","first-page":"639","article-title":"Towards understanding sharpness-aware minimization","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Andriushchenko"},{"key":"ref26","first-page":"3518","article-title":"Making ai forget you: Data deletion in machine learning","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Ginart"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00750"},{"key":"ref28","article-title":"SalUn: Empowering machine unlearning via gradient-based weight saliency in both image classification and generation","author":"Fan","year":"2023","journal-title":"arXiv:2310.12508"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.805"},{"key":"ref30","article-title":"Towards LLM unlearning resilient to relearning attacks: A sharpness-aware minimization perspective and beyond","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","volume":"267","author":"Fan"},{"key":"ref31","article-title":"Negative preference optimization: From catastrophic collapse to effective unlearning","author":"Zhang","year":"2024","journal-title":"arXiv:2404.05868"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-025-00985-0"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3754"},{"key":"ref34","article-title":"Guardrail baselines for unlearning in LLMs","author":"Thaker","year":"2024","journal-title":"arXiv:2403.03329"},{"key":"ref35","article-title":"Open problems in machine unlearning for AI safety","author":"Barez","year":"2025","journal-title":"arXiv:2501.04952"},{"key":"ref36","article-title":"Does your LLM truly unlearn? An embarrassingly simple approach to recover unlearned knowledge","author":"Zhang","year":"2024","journal-title":"arXiv:2410.16454"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3532094"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3646919"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3418581"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3613952"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3186531"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3157139"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3627224"},{"key":"ref44","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. ICLR","author":"Hendrycks"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3361691"},{"key":"ref46","first-page":"14003","article-title":"Can you trust your model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ovadia"},{"key":"ref47","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","volume-title":"Proc. ICLR","author":"Hendrycks"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01096"},{"key":"ref49","article-title":"Input complexity and out-of-distribution detection with likelihood-based generative models","volume-title":"Proc. ICLR","author":"Serr\u00e0"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3127847"},{"key":"ref51","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","volume-title":"Proc. ICLR","author":"Liang"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2754942"},{"key":"ref53","first-page":"20827","article-title":"Out-of-distribution detection with deep nearest neighbors","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref54","article-title":"Out-of-distribution detection and selective generation for conditional language models","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Ren"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00296"},{"key":"ref56","article-title":"ReAct: Out-of-distribution detection with rectified activations","volume-title":"Proc. NeurIPS","volume":"34","author":"Sun"},{"key":"ref57","article-title":"Energy-based out-of-distribution detection for graph neural networks","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Wu"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3520899"},{"key":"ref59","article-title":"BatchEnsemble: An alternative approach to efficient ensemble and lifelong learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wen"},{"key":"ref60","first-page":"15650","article-title":"Poem: Out-of-distribution detection with posterior sampling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ming"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3328478"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378464"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2543"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20610"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3335"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3468874"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01665"},{"key":"ref68","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_15"},{"key":"ref71","article-title":"Dual-Adapter: Training-free dual adaptation for few-shot out-of-distribution detection","author":"Chen","year":"2024","journal-title":"arXiv:2405.16146"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref73","first-page":"4126","article-title":"Machine unlearning via algorithmic stability","volume-title":"Proc. Conf. Learn. Theory","author":"Ullah"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2015.35"},{"key":"ref75","first-page":"1957","article-title":"Towards unbounded machine unlearning","volume-title":"Proc. Adv. neural Inf. Process. Syst.","volume":"36","author":"Kurmanji"},{"key":"ref76","article-title":"Jogging the memory of unlearned models through targeted relearning attacks","volume-title":"Proc. ICML Workshop Found. Models Wild","author":"Hu"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1131"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref79","article-title":"Improving and assessing anomaly detectors for large-scale settings","author":"Hendrycks","year":"2022"},{"key":"ref80","article-title":"Scaling for training time and post-hoc out-of-distribution detection enhancement","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref81","article-title":"ConjNorm: Tractable density estimation for out-of-distribution detection","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Peng"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00487"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref87","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref89","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015","journal-title":"arXiv:1506.03365"},{"key":"ref90","article-title":"TurkerGaze: Crowdsourcing saliency with webcam based eye tracking","author":"Xu","year":"2015","journal-title":"arXiv:1504.06755"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref93","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_40"},{"key":"ref95","article-title":"Generalized few-shot out-of-distribution detection","author":"Li","year":"2025","journal-title":"arXiv:2508.05732"},{"key":"ref96","first-page":"2471","article-title":"In or out? Fixing imagenet out-of-distribution detection evaluation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bitterwolf"},{"key":"ref97","first-page":"5389","article-title":"Do imagenet classifiers generalize to imagenet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11478637.pdf?arnumber=11478637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T19:52:21Z","timestamp":1777319541000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11478637\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":99,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3679195","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}