{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T14:40:32Z","timestamp":1782139232193,"version":"3.54.5"},"reference-count":123,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1109\/tpami.2021.3129870","type":"journal-article","created":{"date-parts":[[2021,11,23]],"date-time":"2021-11-23T21:39:50Z","timestamp":1637703590000},"page":"9298-9314","source":"Crossref","is-referenced-by-count":61,"title":["Factors of Influence for Transfer Learning Across Diverse Appearance Domains and Task Types"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5730-713X","authenticated-orcid":false,"given":"Thomas","family":"Mensink","sequence":"first","affiliation":[{"name":"Google Research, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3288-7377","authenticated-orcid":false,"given":"Jasper","family":"Uijlings","sequence":"additional","affiliation":[{"name":"Google Research, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alina","family":"Kuznetsova","sequence":"additional","affiliation":[{"name":"Google Research, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Gygli","sequence":"additional","affiliation":[{"name":"Google Research, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1942-233X","authenticated-orcid":false,"given":"Vittorio","family":"Ferrari","sequence":"additional","affiliation":[{"name":"Google Research, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.9"},{"key":"ref32","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","author":"ganin","year":"2014","journal-title":"Proc 32nd Int Conf Int Conf Mach Learn"},{"key":"ref31","first-page":"4340","article-title":"Virtual worlds as proxy for multi-object tracking analysis","author":"gaidon","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref30","article-title":"Trash-ICRA19: A bounding box labeled dataset of underwater trash","author":"fulton","year":"0"},{"key":"ref37","first-page":"7620","article-title":"Training neural networks to produce compatible features","author":"gygli","year":"2020","journal-title":"Proc Assoc Adv Artif Intell"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00907"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00459"},{"key":"ref28","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref27","article-title":"The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results","author":"everingham","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00930"},{"key":"ref24","first-page":"6568","article-title":"CenterNet: Keypoint triplets for object detection","author":"duan","year":"2019","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis"},{"key":"ref23","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref101","first-page":"3637","article-title":"Matching networks for one shot learning","author":"vinyals","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00537"},{"key":"ref50","article-title":"Siamese neural networks for one-shot image recognition","author":"koch","year":"2015","journal-title":"Proc Int Conf Mach Learn Workshop"},{"key":"ref51","first-page":"5454","article-title":"Ubernet: Training a ‘universal’ CNN for low-, mid-, and high- level vision using diverse datasets and limited memory","author":"kokkinos","year":"2017","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref59","first-page":"8306","article-title":"Unsupervised domain adaptation for semantic segmentation by content transfer","author":"lee","year":"2020","journal-title":"Proc Assoc Adv Artif Intell"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00295"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.19"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref55","first-page":"12376","article-title":"Towards inheritable models for open-set domain adaptation","author":"kundu","year":"2020","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref54","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00277"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"ref40","article-title":"FCNs in the wild: Pixel-level adversarial and constraint-based adaptation","author":"hoffman","year":"2016"},{"key":"ref4","year":"2012"},{"key":"ref3","year":"0"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1070-x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_12"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"kirkpatrick","year":"2017","journal-title":"Proc Nat Acad Sci USA"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2500224"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.18"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/30.1-2.81"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_5"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref47","article-title":"Novel dataset for fine-grained image categorization","author":"khosla","year":"2011","journal-title":"Proc Workshop Fine-Grained Vis Categorization CVPR Workshop"},{"key":"ref42","article-title":"What makes imagenet good for transfer learning?","author":"huh","year":"2016","journal-title":"Proc Neural Int Process Syst LSCVS Workshop"},{"key":"ref41","article-title":"All you need is a good representation: A multi-level and classifier-centric representation for few-shot learning","author":"huang","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130382"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340821"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00610"},{"key":"ref72","article-title":"Scalable transfer learning with expert models","author":"puigcerver","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00271"},{"key":"ref70","article-title":"On first-order meta-learning algorithms","author":"nichol","year":"2018"},{"key":"ref76","first-page":"506","article-title":"Learning multiple visual domains with residual adapters","author":"rebuffi","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref77","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref74","article-title":"Rapid learning or feature reuse? Towards understanding the effectiveness of MAML","author":"raghu","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref75","article-title":"Optimization as a model for few-shot learning","author":"ravi","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2014.04.009"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00970"},{"key":"ref60","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref61","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","author":"long","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.542"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.83"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref66","article-title":"Supervised transfer learning at scale for medical imaging","author":"mustafa","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref2","year":"0"},{"key":"ref69","article-title":"Domain adaptive transfer learning with specialist models","author":"ngiam","year":"2018"},{"key":"ref1","year":"0"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_27"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref107","article-title":"Accessed: Mar. 21, 2021. Meta-learning: Learning to learn fast","author":"weng","year":"2018","journal-title":"lilianweng github io\/lil-log"},{"key":"ref93","article-title":"Unsupervised domain adaptation through self-supervision","author":"sun","year":"2019"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00578"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref105","first-page":"28","article-title":"iSAID: A large-scale dataset for instance segmentation in aerial images","author":"waqas zamir","year":"2019","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit Workshops"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref104","first-page":"9919","article-title":"Frustratingly simple few-shot object detection","volume":"119","author":"wang","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_38"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00929"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.401"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00395"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.458"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00121"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00190"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00780"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.04.005"},{"key":"ref11","volume":"2","author":"cabon","year":"2020","journal-title":"Virtual kitti"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00753"},{"key":"ref14","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","article-title":"A closer look at few-shot classification","author":"chen","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref118","article-title":"Human pose estimation with spatial contextual information","author":"zhang","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00028"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"ref117","article-title":"A large-scale study of representation learning with the visual task adaptation benchmark","author":"zhai","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_34"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00845"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.167"},{"key":"ref119","article-title":"Stretching domain adaptation: How far is too far?","author":"zhao","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00887"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17285"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref115","article-title":"Wide residual networks","author":"zagoruyko","year":"2016","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref121","article-title":"Objects as points","author":"zhou","year":"0"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00394"},{"key":"ref123","first-page":"3833","article-title":"Rethinking pre-training and self-training","author":"zoph","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref85","first-page":"640","article-title":"Fully convolutional networks for semantic segmentation","author":"shelhamer","year":"2016","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.368"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref88","first-page":"4080","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"2017","journal-title":"Proc 31st Intl Conf Neural Info Process Syst"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9940446\/09625801.pdf?arnumber=9625801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T22:37:00Z","timestamp":1670279820000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9625801\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":123,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3129870","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":[[2022,12,1]]}}}