{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T11:49:19Z","timestamp":1777204159157,"version":"3.51.4"},"reference-count":97,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0160201"],"award-info":[{"award-number":["2022ZD0160201"]}]},{"name":"Shanghai Artificial Intelligence Laboratory, National Natural Science Foundation of China","award":["62106139"],"award-info":[{"award-number":["62106139"]}]},{"name":"State Key Laboratory of High Performance Computing"},{"DOI":"10.13039\/501100007085","name":"National University of Defense Technology","doi-asserted-by":"publisher","award":["202401-11"],"award-info":[{"award-number":["202401-11"]}],"id":[{"id":"10.13039\/501100007085","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tpami.2025.3595676","type":"journal-article","created":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T18:45:09Z","timestamp":1754333109000},"page":"10227-10242","source":"Crossref","is-referenced-by-count":1,"title":["InfoBound: A Provable Information-Bounds Inspired Framework for Both OoD Generalization and OoD Detection"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5155-3442","authenticated-orcid":false,"given":"Lin","family":"Zhu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7177-7885","authenticated-orcid":false,"given":"Yifeng","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zichao","family":"Nie","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7617-0207","authenticated-orcid":false,"given":"Yuan","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiarui","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8863-0810","authenticated-orcid":false,"given":"Qinying","family":"Gu","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinbing","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3331-2302","authenticated-orcid":false,"given":"Chenghu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3129-3953","authenticated-orcid":false,"given":"Nanyang","family":"Ye","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1214\/15-aos1325"},{"key":"ref2","article-title":"WILDS: A benchmark of in-the-wild distribution shifts","author":"Koh","year":"2020"},{"key":"ref3","article-title":"Towards effective semantic ood detection in unseen domains: A domain generalization perspective","author":"Wang","year":"2023"},{"key":"ref4","first-page":"1454","article-title":"Feed two birds with one scone: Exploiting wild data for both out-of-distribution generalization and detection","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bai"},{"key":"ref5","first-page":"14707","article-title":"Likelihood ratios for out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref6","article-title":"A simple fix to mahalanobis distance for improving near-OOD detection","author":"Ren","year":"2021"},{"key":"ref7","article-title":"Contrastive training for improved out-of-distribution detection","author":"Winkens","year":"2020"},{"key":"ref8","first-page":"10 848","article-title":"Training OOD detectors in their natural habitats","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katz-Samuels"},{"key":"ref9","article-title":"AHA: Human-assisted out-of-distribution generalization and detection","author":"Bai","year":"2024"},{"key":"ref10","first-page":"10","article-title":"Domain generalization via invariant feature representation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Muandet"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-46147-8_19"},{"key":"ref12","article-title":"Invariant causal representation learning for out-of-distribution generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lu"},{"key":"ref13","first-page":"24 791","article-title":"Domain adaptation with invariant representation learning: What transformations to learn?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Stojanov"},{"key":"ref14","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019"},{"key":"ref15","article-title":"Improving the generalization of adversarial training with domain adaptation","author":"Song","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00566"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_8"},{"key":"ref18","first-page":"6450","article-title":"Domain generalization via model-agnostic learning of semantic features","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dou"},{"key":"ref19","article-title":"Learning gradient-based mixup towards flatter minima for domain generalization","author":"Peng","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16829"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_12"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"ref23","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"issue":"1","key":"ref24","first-page":"1309","article-title":"Invariant models for causal transfer learning","volume":"19","author":"Rojas-Carulla","year":"2018","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"ref25","first-page":"46","article-title":"Domain generalization by marginal transfer learning","volume":"22","author":"Blanchard","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2021\/628","article-title":"Generalizing to unseen domains: A survey on domain generalization","author":"Wang","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6024"},{"key":"ref28","first-page":"8265","article-title":"Ensemble of averages: Improving model selection and boosting performance in domain generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Arpit"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01555"},{"key":"ref30","article-title":"In search of lost domain generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gulrajani"},{"key":"ref31","article-title":"OOD-bench: Benchmarking and understanding out-of-distribution generalization datasets and algorithms","author":"Ye","year":"2021"},{"key":"ref32","article-title":"Domain generalization by learning and removing domain-specific features","author":"Ding","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.293"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_18"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_26"},{"key":"ref36","first-page":"3437","article-title":"Reasoning about generalization via conditional mutual information","volume-title":"Proc. Conf. Learn. Theory","author":"Steinke"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3175018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00972"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00308"},{"key":"ref40","article-title":"Slicing mutual information generalization bounds for neural networks","author":"Nadjahi","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956548"},{"key":"ref42","first-page":"20 758","article-title":"Boosting out-of-distribution detection with typical features","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref43","first-page":"21 464","article-title":"Energy-based out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref44","first-page":"144","article-title":"ReAct: Out-of-distribution detection with rectified activations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref45","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"Hendrycks","year":"2016"},{"key":"ref46","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","author":"Liang","year":"2017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00487"},{"key":"ref48","first-page":"20 827","article-title":"Out-of-distribution detection with deep nearest neighbors","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00493"},{"key":"ref50","first-page":"7047","article-title":"Predictive uncertainty estimation via prior networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Malinin"},{"key":"ref51","article-title":"VOS: Learning what you don\u2019t know by virtual outlier synthesis","author":"Du","year":"2022"},{"key":"ref52","first-page":"20 434","article-title":"SIREN: Shaping representations for detecting out-of-distribution objects","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Du"},{"key":"ref53","first-page":"15 650","article-title":"POEM: Out-of-distribution detection with posterior sampling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ming"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02117-4"},{"key":"ref55","first-page":"32 598","article-title":"OpenOOD: Benchmarking generalized out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref56","article-title":"OpenOOD v1.5: Enhanced benchmark for out-of-distribution detection","author":"Zhang","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00887"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2958324"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref61","article-title":"Prototypical contrastive learning of unsupervised representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref62","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref63","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref64","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref65","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks"},{"key":"ref66","article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"Proc. NIPS Workshop Deep Learn. Unsupervised Feature Learn.","author":"Yuval"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref68","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref71","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02036-4"},{"key":"ref75","article-title":"Amortized Prompt: Guide clip to domain transfer learning","author":"Zhang","year":"2021"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref79","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref80","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref85","article-title":"DetectBench: An object detection benchmark for OOD generalization algorithms","author":"Wu","year":"2022"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02154"},{"key":"ref87","first-page":"7167","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref88","first-page":"8491","article-title":"Detecting out-of-distribution examples with gram matrices","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sastry"},{"key":"ref89","first-page":"11 839","article-title":"CSI: Novelty detection via contrastive learning on distributionally shifted instances","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tack"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"ref91","article-title":"Distinction maximization loss: Efficiently improving out-of-distribution detection and uncertainty estimation by replacing the loss and calibrating","author":"Mac\u00eado","year":"2022"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref93","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref95","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"ref96","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019"},{"key":"ref97","article-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","author":"Kumar","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11192800\/11112669.pdf?arnumber=11112669","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:36:35Z","timestamp":1759772195000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11112669\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":97,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3595676","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":[[2025,11]]}}}