{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T18:06:16Z","timestamp":1794593176273,"version":"4.9.1"},"reference-count":266,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tkde.2022.3178128","type":"journal-article","created":{"date-parts":[[2022,5,26]],"date-time":"2022-05-26T19:38:32Z","timestamp":1653593912000},"page":"1-1","source":"Crossref","is-referenced-by-count":799,"title":["Generalizing to Unseen Domains: A Survey on Domain Generalization"],"prefix":"10.1109","author":[{"given":"Jindong","family":"Wang","sequence":"first","affiliation":[{"name":"Machine Learning, Microsoft Research Asia, 216064 Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cuiling","family":"Lan","sequence":"additional","affiliation":[{"name":"Machine Learning, Microsoft Research Asia, 216064 Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"Machine learning area, Microsoft Research Asia, 216064 Beijing, Beijing, China, 100080"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yidong","family":"Ouyang","sequence":"additional","affiliation":[{"name":"School of Data Science, Chinese University of Hong Kong, Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Qin","sequence":"additional","affiliation":[{"name":"Machine Learning, Microsoft Research Asia, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wang","family":"Lu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[{"name":"Machine Learning, Microsoft Research Asia, 216064 Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Illinois at Chicago, and Institute for Data Science, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","article-title":"Frustratingly simple domain generalization via image stylization","author":"somavarapu","year":"2020"},{"key":"ref207","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00067"},{"key":"ref208","first-page":"4077","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00087"},{"key":"ref205","article-title":"Causal generative domain adaptation networks","author":"gong","year":"2018"},{"key":"ref58","article-title":"Out-of-domain generalization from a single source: A uncertainty quantification approach","author":"peng","year":"2021"},{"key":"ref206","article-title":"Conditional variance penalties and domain shift robustness","volume":"1050","author":"heinze-deml","year":"2019","journal-title":"Stat"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00876"},{"key":"ref203","first-page":"819","article-title":"Domain adaptation under target and conditional shift","author":"zhang","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00029"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9542"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01415"},{"key":"ref201","article-title":"Variational disentanglement for domain generalization","author":"wang","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00950"},{"key":"ref202","first-page":"1255","article-title":"On causal and anticausal learning","author":"sch\u00f6lkopf","year":"2012","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref209","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","author":"santoro","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00621"},{"key":"ref211","article-title":"Distributionally robust optimization: A review","author":"rahimian","year":"2019"},{"key":"ref51","first-page":"20210","article-title":"Model-based domain generalization","author":"robey","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref50","article-title":"Image alignment in unseen domains via domain deep generalization","author":"truong","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00403"},{"key":"ref218","article-title":"Federated learning with domain generalization","author":"zhang","year":"2021"},{"key":"ref45","first-page":"3574","article-title":"Learn to expect the unexpected: Probably approximately correct domain generalization","author":"garg","year":"2021","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00107"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053273"},{"key":"ref216","first-page":"51","article-title":"Encouraging intra-class diversity through a reverse contrastive loss for better single-source domain generalization","author":"duboudin","year":"2021","journal-title":"Proc IEEE Int Conf Comput Vis Workshops"},{"key":"ref47","article-title":"DomainMix: Learning generalizable person re-identification without human annotations","author":"wang","year":"2021","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref217","article-title":"Semi-supervised domain generalization in real world: New benchmark and strong baseline","author":"lin","year":"2021"},{"key":"ref42","article-title":"Recognition in unseen domains: Domain generalization via universal non-volume preserving models","author":"truong","year":"2019"},{"key":"ref214","first-page":"2215","article-title":"On calibration and out-of-domain generalization","author":"wald","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref41","first-page":"2590","article-title":"A unified feature disentangler for multi-domain image translation and manipulation","author":"liu","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00883"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00621"},{"key":"ref212","first-page":"1","article-title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization","author":"sagawa","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_33"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref49","first-page":"1","article-title":"Domain generalization with mixstyle","author":"zhou","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3112012"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref4","article-title":"Towards out-of-distribution generalization: A survey","author":"shen","year":"2021"},{"key":"ref3","article-title":"Domain generalization in vision: A survey","author":"zhou","year":"2021"},{"key":"ref6","article-title":"Domain generalization by marginal transfer learning","volume":"22","author":"blanchard","year":"2021","journal-title":"J Mach Learn Res"},{"key":"ref5","article-title":"Generalized out-of-distribution detection: A survey","author":"yang","year":"2021"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00851"},{"key":"ref221","first-page":"18408","article-title":"FlexMatch: Boosting semi-supervised learning with curriculum pseudo labeling","author":"zhang","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92273-3_7"},{"key":"ref222","first-page":"1856","article-title":"ReMoS: Reducing defect inheritance in transfer learning via relevant model slicing","author":"zhang","year":"2022","journal-title":"Proc 4th Int Conf Software Engineering"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01257"},{"key":"ref220","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","author":"sohn","year":"2020","journal-title":"Proc 34th Int Conf Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00143"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00210"},{"key":"ref37","first-page":"1","article-title":"Generalizing across domains via cross-gradient training","author":"shankar","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref36","first-page":"666","article-title":"Domain generalization using shape representation","author":"nazari","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00682"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794443"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7003"},{"key":"ref38","first-page":"5334","article-title":"Generalizing to unseen domains via adversarial data augmentation","author":"volpi","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5152-4"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1360\/N112018-00312","article-title":"A decadal survey of zero-shot image classification","volume":"49","author":"ji","year":"2019","journal-title":"Sci Sinica Inf"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.5.851"},{"key":"ref25","first-page":"527","article-title":"Support and invertibility in domain-invariant representations","author":"johansson","year":"2019","journal-title":"Proc 22nd Int Conf Artif Intell Statist"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_12"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3293318"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.574"},{"key":"ref28","article-title":"A generalization error bound for multi-class domain generalization","author":"deshmukh","year":"2019"},{"key":"ref27","first-page":"10","article-title":"Domain generalization via invariant feature representation","author":"muandet","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00219"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475311"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17416"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413815"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01141"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6846"},{"key":"ref126","first-page":"8024","article-title":"Towards principled disentanglement for domain generalization","author":"zhang","year":"2021","journal-title":"Proc ICML Mach Learn Data Workshop"},{"key":"ref247","first-page":"102","article-title":"Playing for data: Ground truth from computer games","author":"richter","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01026"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00858"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107124"},{"key":"ref124","first-page":"322","article-title":"DIVA: Domain invariant variational autoencoders","author":"ilse","year":"2020","journal-title":"Proc 3rd Conf Med Imag Deep Learn"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbmt.2007.02.002"},{"key":"ref98","article-title":"Domain adversarial neural networks for domain generalization: When it works and how to improve","author":"sicilia","year":"2021"},{"key":"ref125","first-page":"5102","article-title":"Domain agnostic learning with disentangled representations","author":"peng","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00258"},{"key":"ref133","first-page":"16846","article-title":"Recovering latent causal factor for generalization to distributional shifts","author":"sun","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref254","article-title":"DeepDG: Deep domain generalization toolkit","author":"wang","year":"2022"},{"key":"ref92","first-page":"59:1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00533"},{"key":"ref255","article-title":"Everything about transfer learning and domain adapation","author":"wang","year":"2022"},{"key":"ref95","article-title":"Domain generalization via entropy regularization","author":"zhao","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref131","article-title":"A causal view on robustness of neural networks","author":"zhang","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1038\/npre.2008.2298.1"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_38"},{"key":"ref132","first-page":"6155","article-title":"Learning causal semantic representation for out-of-distribution prediction","author":"liu","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.3115\/1610075.1610094"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00081"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00820"},{"key":"ref251","article-title":"OpenAI gym","author":"brockman","year":"2016"},{"key":"ref91","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","author":"ganin","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.05.014"},{"key":"ref89","first-page":"1","article-title":"A study of domain generalization on ultrasound-based multi-class segmentation of arteries, veins, ligaments, and nerves using transfer learning","author":"chen","year":"2020","journal-title":"Proc Mach Learn Health NeurIPS"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451318"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/BCI51272.2021.9385322"},{"key":"ref137","first-page":"187","article-title":"Domain generalization with domain-specific aggregation modules","author":"d\u2019innocente","year":"2018","journal-title":"Proc German Conf Pattern Recognit"},{"key":"ref258","first-page":"9898","article-title":"Continuously indexed domain adaptation","author":"wang","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref85","first-page":"1","article-title":"Zero shot domain generalization","author":"maniyar","year":"2020","journal-title":"Proc Brit Mach Vis Virtual Conf"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00642"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66415-2_39"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103757"},{"key":"ref135","article-title":"Causality-inspired single-source domain generalization for medical image segmentation","author":"ouyang","year":"2021"},{"key":"ref256","first-page":"1","article-title":"Learning explanations that are hard to vary","author":"parascandolo","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref87","first-page":"1","article-title":"In search of lost domain generalization","author":"gulrajani","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107383"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06080-w"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00024"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.046"},{"key":"ref265","first-page":"2427","article-title":"Test-time classifier adjustment module for model-agnostic domain generalization","author":"iwasawa","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00811"},{"key":"ref145","article-title":"Domain generalization via semi-supervised meta learning","author":"sharifi-noghabi","year":"2020"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01273"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747363"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01411"},{"key":"ref263","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref83","first-page":"1","article-title":"Feature alignment and restoration for domain generalization and adaptation","author":"jin","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref143","first-page":"6447","article-title":"Domain generalization via model-agnostic learning of semantic features","author":"dou","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref264","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03341-5_3"},{"key":"ref261","first-page":"1","article-title":"CrossMatch: Cross-classifier consistency regularization for open-set single domain generalization","author":"zhu","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2809700"},{"key":"ref262","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482315"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_28"},{"key":"ref79","article-title":"Unsupervised domain generalization for person re-identification: A domain-specific adaptive framework","author":"qi","year":"2021"},{"key":"ref108","article-title":"Out-of-distribution prediction with invariant risk minimization: The limitation and an effective fix","author":"guo","year":"2021"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413872"},{"key":"ref109","first-page":"1","article-title":"Empirical or invariant risk minimization? A sample complexity perspective","author":"ahuja","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref106","first-page":"5815","article-title":"Out-of-distribution generalization via risk extrapolation (REx)","author":"krueger","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0186-1"},{"key":"ref107","first-page":"1","article-title":"Representation learning via invariant causal mechanisms","author":"mitrovic","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref228","first-page":"3811","article-title":"On the out-of-distribution generalization of probabilistic image modelling","author":"zhang","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191364"},{"key":"ref104","article-title":"Invariant risk minimization","author":"arjovsky","year":"2019"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2020.2992829"},{"key":"ref105","first-page":"3438","article-title":"Invariance principle meets information bottleneck for out-of-distribution generalization","author":"ahuja","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.2988604"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_5"},{"key":"ref102","article-title":"Adversarial target-invariant representation learning for domain generalization","author":"albuquerque","year":"2019"},{"key":"ref223","first-page":"1","article-title":"The connection between out-of-distribution generalization and privacy of ML models","author":"mahajan","year":"2021","journal-title":"Proc Workshop Privacy Preserving Mach Learn NeurIPS"},{"key":"ref76","first-page":"7313","article-title":"Domain generalization using causal matching","author":"mahajan","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206635"},{"key":"ref224","first-page":"1","volume":"13","author":"yang","year":"2019","journal-title":"Federated Learning"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3104379"},{"key":"ref111","first-page":"1","article-title":"The risks of invariant risk minimization","author":"rosenfeld","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00321"},{"key":"ref112","first-page":"145","article-title":"Invariant risk minimization games","author":"ahuja","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2020.3016068"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.208"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00566"},{"key":"ref110","article-title":"An empirical study of invariant risk minimization","author":"choe","year":"2020"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.609"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_45"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.293"},{"key":"ref117","first-page":"7728","article-title":"Efficient domain generalization via common-specific low-rank decomposition","author":"piratla","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.34133\/2020\/3521852"},{"key":"ref69","article-title":"Batch normalization embeddings for deep domain generalization","author":"seg\u00f9","year":"2020"},{"key":"ref118","article-title":"Domain2Vec: Deep domain generalization","author":"deshmukh","year":"2018"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1145\/3308560.3317593"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599532"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_12"},{"key":"ref236","first-page":"1","article-title":"RxRx1: An image set for cellular morphological variation across many experimental batches","author":"taylor","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11682"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.477"},{"key":"ref237","first-page":"1","article-title":"Open graph benchmark: Datasets for machine learning on graphs","author":"hu","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref66","first-page":"292","article-title":"Domain generalization via multidomain discriminant analysis","author":"hu","year":"2019","journal-title":"Proc Conf Uncertainty of Artificial Intelligence"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_41"},{"key":"ref234","article-title":"The iWildCam 2020 competition dataset","author":"beery","year":"2020"},{"key":"ref65","first-page":"1455","article-title":"Robust domain generalisation by enforcing distribution invariance","author":"erfani","year":"2016","journal-title":"Proc 25th Int Joint Conf Artif Intell"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2704624"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2867350"},{"key":"ref60","article-title":"Domain generalization by marginal transfer learning","author":"blanchard","year":"2017"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2758199"},{"key":"ref243","first-page":"1","article-title":"CodeXGLUE: A machine learning benchmark dataset for code understanding and generation","author":"lu","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00361"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1145\/3022671.2984041"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.17"},{"key":"ref120","article-title":"Domain and content adaptive convolution for domain generalization in medical image segmentation","author":"hu","year":"2021"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-16185-w"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-19258-1_28"},{"key":"ref121","first-page":"10424","article-title":"Learning a universal template for few-shot dataset generalization","author":"triantafillou","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1018"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00646"},{"key":"ref168","first-page":"1","article-title":"Understanding out-of-distribution: A perspective of data dynamics","author":"adila","year":"2021","journal-title":"Proc Int Conf Neural Inf Process Syst Workshop"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref170","first-page":"1","article-title":"Semi-supervised domain generalization with stochastic stylematch","author":"zhou","year":"2021","journal-title":"Proc Int Conf Neural Inf Process Syst Workshop"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref175","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"gretton","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref176","article-title":"Wasserstein auto-encoders","author":"tolstikhin","year":"2017"},{"key":"ref173","first-page":"1","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00122"},{"key":"ref171","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2013"},{"key":"ref172","first-page":"2672","article-title":"Generative adversarial networks","author":"goodfellow","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0022"},{"key":"ref180","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"cortes","year":"1995","journal-title":"Mach Learn"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2091281"},{"key":"ref188","article-title":"Deep domain confusion: Maximizing for domain invariance","author":"tzeng","year":"2014"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240512"},{"key":"ref186","article-title":"Frustratingly easy person re-identification: Generalizing person re-ID in practice","author":"jia","year":"2019","journal-title":"Proc 30th Brit Mach Vis Conf"},{"key":"ref187","first-page":"2563","article-title":"Batch-instance normalization for adaptively style-invariant neural networks","author":"nam","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM51629.2021.00203"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_29"},{"key":"ref182","article-title":"Domain generalization with optimal transport and metric learning","author":"zhou","year":"2020"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00672"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506516"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00153"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.33"},{"key":"ref155","first-page":"1","article-title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization","author":"sagawa","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref156","first-page":"5637","article-title":"WILDS: A benchmark of in-the-wild distribution shifts","author":"koh","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3157441"},{"key":"ref154","first-page":"6781","article-title":"Just train twice: Improving group robustness without training group information","author":"liu","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref151","first-page":"1","article-title":"Gradient matching for domain generalization","author":"shi","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref152","article-title":"Fishr: Invariant gradient variances for out-of-distribution generalization","author":"rame","year":"2021"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_8"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00948"},{"key":"ref157","first-page":"1","article-title":"Class-conditioned domain generalization via wasserstein distributional robust optimization","author":"wang","year":"2021","journal-title":"Proc RobustML Workshop ICLR"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00233"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01504"},{"key":"ref167","first-page":"23519","article-title":"Towards a theoretical framework of out-of-distribution generalization","author":"ye","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref164","first-page":"12356","article-title":"Can subnetwork structure be the key to out-of-distribution generalization?","author":"zhang","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref165","first-page":"22405","article-title":"SWAD: Domain generalization by seeking flat minima","author":"cha","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref162","first-page":"1","article-title":"Generalized convolutional forest networks for domain generalization and visual recognition","author":"ryu","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00135"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475271"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87234-2_10"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2347059"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.083"},{"key":"ref15","first-page":"5149","article-title":"Meta-learning in neural networks: A survey","volume":"44","author":"hospedales","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1023\/A:1019956318069"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-016-0043-6","article-title":"A survey of transfer learning","volume":"3","author":"weiss","year":"2016","journal-title":"J Big Data"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"ref16","article-title":"Meta-learning: A survey","author":"vanschoren","year":"2018"},{"key":"ref19","first-page":"3915","article-title":"Feature-critic networks for heterogeneous domain generalization","author":"li","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","first-page":"998","article-title":"MetaReg: Towards domain generalization using meta-regularization","author":"balaji","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref1","author":"qui\u00f1onero-candela","year":"2009","journal-title":"Dataset Shift in Machine Learning"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10306"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1145\/3360309"},{"key":"ref199","article-title":"Dynamically decoding source domain knowledge for unseen domain generalization","author":"kang","year":"2021"},{"key":"ref197","first-page":"21","article-title":"Invariant policy optimization: Towards stronger generalization in reinforcement learning","author":"sonar","year":"2021","journal-title":"Proc 3rd Annu Conf Learn Dyn Control"},{"key":"ref198","first-page":"21189","article-title":"Exploiting domain-specific features to enhance domain generalization","author":"bui","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref195","first-page":"1","article-title":"A learned representation for artistic style","author":"dumoulin","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref196","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00219"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.437"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/4358933\/09782500.pdf?arnumber=9782500","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,7]],"date-time":"2023-07-07T22:21:40Z","timestamp":1688768500000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9782500\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":266,"URL":"https:\/\/doi.org\/10.1109\/tkde.2022.3178128","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}