{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T14:31:42Z","timestamp":1770733902322,"version":"3.49.0"},"reference-count":143,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572313"],"award-info":[{"award-number":["62572313"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106139"],"award-info":[{"award-number":["62106139"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2018AAA0101200"],"award-info":[{"award-number":["2018AAA0101200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61829201"],"award-info":[{"award-number":["61829201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61832013"],"award-info":[{"award-number":["61832013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61960206002"],"award-info":[{"award-number":["61960206002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62061146002"],"award-info":[{"award-number":["62061146002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42050105"],"award-info":[{"award-number":["42050105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032020"],"award-info":[{"award-number":["62032020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Program of Shanghai","award":["18XD1401800"],"award-info":[{"award-number":["18XD1401800"]}]},{"name":"Shanghai Key Laboratory of Scalable Computing and Systems"},{"name":"BIREN Tech"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tpami.2025.3628027","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:44:48Z","timestamp":1762195488000},"page":"2566-2580","source":"Crossref","is-referenced-by-count":0,"title":["OoDBench+: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3129-3953","authenticated-orcid":false,"given":"Nanyang","family":"Ye","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Kaican","family":"Li","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5064-7062","authenticated-orcid":false,"given":"Fan","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Jundong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8139-0431","authenticated-orcid":false,"given":"Haoyue","family":"Bai","sequence":"additional","affiliation":[{"name":"University of Wisconsin Madison, Madison, WI, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6321-9614","authenticated-orcid":false,"given":"Runpeng","family":"Yu","sequence":"additional","affiliation":[{"name":"National University of Singapore,, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2752-5942","authenticated-orcid":false,"given":"Lanqing","family":"Hong","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab., Shatin, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6404-6441","authenticated-orcid":false,"given":"Fengwei","family":"Zhou","sequence":"additional","affiliation":[{"name":"OPPO, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8492-3069","authenticated-orcid":false,"given":"Zhenguo","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab., Shatin, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6254-2388","authenticated-orcid":false,"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0357-8356","authenticated-orcid":false,"given":"Xinbing","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"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"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref3","article-title":"Do imageNet classifiers generalize to imageNet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref4","article-title":"Intriguing properties of neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Szegedy"},{"key":"ref5","article-title":"Wilds: A benchmark of in-the-wild distribution shifts","author":"Koh","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref7","article-title":"Learning de-biased representations with biased representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bahng"},{"key":"ref8","article-title":"Out-of-distribution generalization via risk extrapolation (rex)","author":"Krueger","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_28"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-17478-w"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12752"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569387"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917269"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00498"},{"key":"ref15","article-title":"Security of deep learning based lane keeping system under physical-world adversarial attack","author":"Sato","year":"2020"},{"key":"ref16","article-title":"Benchmarking robustness in object detection: Autonomous driving when winter is coming","author":"Michaelis","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2020.100270"},{"key":"ref18","first-page":"2178","article-title":"Generalizing from several related classification tasks to a new unlabeled sample","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Blanchard","year":"2011"},{"key":"ref19","first-page":"I-10","article-title":"Domain generalization via invariant feature representation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Muandet"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/628"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3195549"},{"key":"ref22","first-page":"39","article-title":"Causal inference","volume-title":"Proc. NeurIPS Workshop Causality","volume":"6","author":"Pearl","year":"2008"},{"key":"ref23","volume-title":"Elements of Causal Inference: Foundations and Learning Algorithms","author":"Peters","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00533"},{"key":"ref25","article-title":"Out of distribution generalization in machine learning","author":"Arjovsky","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00566"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_8"},{"key":"ref28","article-title":"Towards out-of-distribution generalization: A survey","author":"Shen","year":"2021"},{"key":"ref29","article-title":"Reducing domain gap via style-agnostic networks","author":"Nam","year":"2019"},{"key":"ref30","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946704"},{"key":"ref32","article-title":"Domain generalization by marginal transfer learning","author":"Blanchard","year":"2017"},{"key":"ref33","article-title":"Learning explanations that are hard to vary","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Parascandolo"},{"key":"ref34","article-title":"Distributionally robust neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sagawa"},{"key":"ref35","article-title":"In search of lost domain generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gulrajani"},{"key":"ref36","volume-title":"Statistical Learning Theory","author":"Vapnik","year":"1998"},{"key":"ref37","article-title":"An empirical study on distribution shift robustness from the perspective of pre-training and data augmentation","volume-title":"Proc. NeurIPS 2022 Workshop Distrib. Shifts: Connecting Methods Appl.","author":"Liu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref42","article-title":"Empirical or invariant risk minimization? A sample complexity perspective","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ahuja"},{"key":"ref43","first-page":"6155","article-title":"Learning causal semantic representation for out-of-distribution prediction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref44","article-title":"Representation learning via invariant causal mechanisms","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mitrovic"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2022.3224067"},{"key":"ref46","article-title":"Regularized learning for domain adaptation under label shifts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Azizzadenesheli"},{"key":"ref47","volume-title":"Causality: Models, Reasoning and Inference","author":"Pearl","year":"2000"},{"key":"ref48","first-page":"23527","article-title":"Certifying out-of-domain generalization for blackbox functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Weber"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177728190"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177704472"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198517962.001.0001"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3406325.3465355"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01501"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00823"},{"key":"ref55","article-title":"Domain generalization via entropy regularization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref57","article-title":"Out-of-distribution generalization with maximal invariant predictor","author":"Koyama","year":"2020"},{"key":"ref58","article-title":"Improve unsupervised domain adaptation with mixup training","author":"Yan","year":"2020"},{"key":"ref59","article-title":"Adaptive risk minimization: A meta-learning approach for tackling group distribution shift","author":"Zhang","year":"2020"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093315"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107383"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6123"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00233"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16829"},{"key":"ref69","first-page":"145","article-title":"Invariant risk minimization games","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ahuja"},{"key":"ref70","article-title":"Gradient starvation: A learning proclivity in neural networks","author":"Pezeshki","year":"2020"},{"key":"ref71","first-page":"6450","article-title":"Domain generalization via model-agnostic learning of semantic features","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dou"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref74","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rosenfeld"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1998.710701"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0069"},{"key":"ref77","first-page":"22405","article-title":"SWAD: Domain generalization by seeking flat minima","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cha"},{"key":"ref78","article-title":"Model monitoring and robustness of in-use machine learning models: Quantifying data distribution shifts using population stability index","author":"Khademi","year":"2023"},{"key":"ref79","article-title":"Quantifying and alleviating distribution shifts in foundation models on review classification","volume-title":"Proc. NeurIPS 2021 Workshop Distrib. Shifts: Connecting Methods Appl.","author":"Chawla"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0022"},{"key":"ref81","article-title":"A fine-grained analysis on distribution shift","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wiles"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-46147-8_19"},{"key":"ref83","article-title":"Adversarial target-invariant representation learning for domain generalization","author":"Albuquerque","year":"2019"},{"key":"ref84","article-title":"Generalizing to unseen domains via distribution matching","author":"Albuquerque","year":"2019"},{"key":"ref85","first-page":"1006","article-title":"MetaReg: Towards domain generalization using meta-regularization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Balaji"},{"key":"ref86","first-page":"3915","article-title":"Feature-critic networks for heterogeneous domain generalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref87","article-title":"Generalizing across domains via cross-gradient training","author":"Shankar","year":"2018"},{"key":"ref88","first-page":"24791","article-title":"Domain invariant representation learning with domain density transformations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Nguyen"},{"key":"ref89","first-page":"20210","article-title":"Model-based domain generalization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Robey"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_33"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"ref92","article-title":"Fishr: Invariant gradient variances for out-of-distribution generalization","author":"Rame","year":"2021"},{"key":"ref93","article-title":"Gradient matching for domain generalization","author":"Shi","year":"2021"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_10"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7003"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01411"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11682"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599532"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00029"},{"key":"ref101","article-title":"Frustratingly simple domain generalization via image stylization","author":"Somavarapu","year":"2020"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00087"},{"key":"ref103","article-title":"Domain generalization with mixstyle","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475271"},{"key":"ref105","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00876"},{"key":"ref107","first-page":"5339","article-title":"Generalizing to unseen domains via adversarial data augmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Volpi"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01257"},{"key":"ref109","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":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00948"},{"key":"ref111","article-title":"Asymmetry learning for counterfactually-invariant classification in ood tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mouli"},{"key":"ref112","first-page":"16846","article-title":"Recovering latent causal factor for generalization to distributional shifts","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00941"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3462293"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11662"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33486-3_3"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186133"},{"key":"ref118","first-page":"107","article-title":"The cost of fairness in binary classification","volume-title":"Proc. Conf. Fairness Accountability Transparency","author":"Menon"},{"key":"ref119","first-page":"2879","article-title":"Stable and fair classification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref120","first-page":"6373","article-title":"Fairness without harm: Decoupled classifiers with preference guarantees","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ustun"},{"key":"ref121","first-page":"3323","article-title":"Equality of opportunity in supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hardt"},{"key":"ref122","article-title":"Fairness-aware classification: Criterion, convexity, and bounds","author":"Wu","year":"2018"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.2307\/2282952"},{"key":"ref124","article-title":"Empirical Bernstein bounds and sample variance penalization","author":"Maurer","year":"2009"},{"key":"ref125","article-title":"Scaling neural tangent kernels via sketching and random features","author":"Zandieh","year":"2021"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2867350"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00646"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00842"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00894"},{"key":"ref131","article-title":"Fair mixup: Fairness via interpolation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chuang"},{"key":"ref132","article-title":"Bdd100k: A diverse driving video database with scalable annotation tooling","author":"Yu","year":"2018"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1072-8"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3014013"},{"key":"ref136","first-page":"4069","article-title":"Does invariant risk minimization capture invariance?","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Kamath"},{"key":"ref137","article-title":"A causal framework to unify common domain generalization approaches","author":"Zhang","year":"2023"},{"key":"ref138","article-title":"Improved fine-tuning by better leveraging pre-training data","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2022"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3389497"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00965"},{"key":"ref141","first-page":"6941","article-title":"Compositional generalization from first principle","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wiedemer"},{"key":"ref142","first-page":"5338","article-title":"Concept bottleneck models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"key":"ref143","first-page":"66025","article-title":"Dual risk minimization: Towards next-level robustness in fine-tuning zero-shot models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref144","article-title":"Dual risk minimization: Towards next-level robustness in fine-tuning zero-shot models","author":"Chu","year":"2025"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11372200\/11224007.pdf?arnumber=11224007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:05:52Z","timestamp":1770671152000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11224007\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":143,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3628027","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":[[2026,3]]}}}