{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:25:39Z","timestamp":1782995139185,"version":"3.54.5"},"reference-count":276,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100021856","name":"European Union through the Italian National Recovery and Resilience Plan (NRRP) of NextGenerationEU partnership on \u201cTelecommunications of the Future\u201d","doi-asserted-by":"publisher","award":["PE0000001"],"award-info":[{"award-number":["PE0000001"]}],"id":[{"id":"10.13039\/501100021856","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3310400","type":"journal-article","created":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T17:26:39Z","timestamp":1693416399000},"page":"94863-94884","source":"Crossref","is-referenced-by-count":36,"title":["Federated Learning in Computer Vision"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6501-9437","authenticated-orcid":false,"given":"Donald","family":"Shenaj","sequence":"first","affiliation":[{"name":"Department of Information Engineering, University of Padova, Padua, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1390-8419","authenticated-orcid":false,"given":"Giulia","family":"Rizzoli","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Padova, Padua, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9502-2389","authenticated-orcid":false,"given":"Pietro","family":"Zanuttigh","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Padova, Padua, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3220757"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01626"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1561\/0400000042","article-title":"The algorithmic foundations of differential privacy","volume":"9","author":"dwork","year":"2014","journal-title":"Foundations and Trends\ufffd in Theoretical Computer Science"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1145\/3510033"},{"key":"ref59","author":"everingham","year":"2012","journal-title":"The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3257562"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00986"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00431-6"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20819"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_10"},{"key":"ref204","article-title":"Federated learning from pre-trained models: A contrastive learning approach","author":"tan","year":"2022","journal-title":"arXiv 2209 10083"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00780"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3568538"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3565010.3569062"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00919"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-011-0391-3"},{"key":"ref210","first-page":"1","article-title":"The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions","volume":"5","author":"tschandl","year":"2018","journal-title":"Data Science Journal"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00383"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00992"},{"key":"ref46","article-title":"Mitigating data heterogeneity in federated learning with data augmentation","author":"de luca","year":"2022","journal-title":"arXiv 2206 09979"},{"key":"ref218","article-title":"Federated learning with matched averaging","author":"wang","year":"2020","journal-title":"arXiv 2002 06440"},{"key":"ref45","article-title":"CINIC-10 is not ImageNet or CIFAR-10","author":"darlow","year":"2018","journal-title":"arXiv 1810 03505"},{"key":"ref219","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume":"33","author":"wang","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref48","article-title":"HeteroFL: Computation and communication efficient federated learning for heterogeneous clients","author":"diao","year":"2020","journal-title":"arXiv 2010 01264"},{"key":"ref216","first-page":"16070","article-title":"Attack of the tails: Yes, you really can backdoor federated learning","volume":"33","author":"wang","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.11.023"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966217"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57959-7"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3010287"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01955"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_41"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"ref49","article-title":"An efficient industrial federated learning framework for AIoT: A face recognition application","author":"ding","year":"2022","journal-title":"arXiv 2206 13398"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60548-3_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00247"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30695-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3038676"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IJCB52358.2021.9484386"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1117\/12.2293584"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3009075"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-18-1233"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547762"},{"key":"ref101","article-title":"Improving federated learning personalization via model agnostic meta learning","author":"jiang","year":"2019","journal-title":"arXiv 1909 12488"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-76550-z"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01568"},{"key":"ref220","article-title":"SlowMo: Improving communication-efficient distributed SGD with slow momentum","author":"wang","year":"2019","journal-title":"arXiv 1910 00643"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00044"},{"key":"ref34","first-page":"1","article-title":"On the importance and applicability of pre-training for federated learning","author":"chen","year":"2023","journal-title":"Proc 11th Int Conf Learn Represent"},{"key":"ref37","article-title":"Rethinking Atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv 1706 05587"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539384"},{"key":"ref31","article-title":"The best of both worlds: Accurate global and personalized models through federated learning with data-free hyper-knowledge distillation","author":"chen","year":"2023","journal-title":"arXiv 2301 08968"},{"key":"ref30","article-title":"Federated meta-learning with fast convergence and efficient communication","author":"chen","year":"2018","journal-title":"arXiv 1802 07876"},{"key":"ref33","first-page":"1","article-title":"On bridging generic and personalized federated learning for image classification","author":"chen","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref32","article-title":"FedBE: Making Bayesian model ensemble applicable to federated learning","author":"chen","year":"2020","journal-title":"arXiv 2009 01974"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.220"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97909-0_46"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_38"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref26","article-title":"LEAF: A benchmark for federated settings","author":"caldas","year":"2018","journal-title":"arXiv 1812 01097"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00309"},{"key":"ref20","first-page":"5","article-title":"NCI-ISBI 2013 challenge: Automated segmentation of prostate structures","volume":"370","author":"bloch","year":"2015","journal-title":"Cancer Imag Arch"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.04.005"},{"key":"ref21","first-page":"374","article-title":"Towards federated learning at scale: System design","volume":"1","author":"bonawitz","year":"2019","journal-title":"Proc Mach Learn Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3159236"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01173"},{"key":"ref200","article-title":"Cross-domain federated object detection","author":"su","year":"2022","journal-title":"arXiv 2206 14996"},{"key":"ref128","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"li","year":"2020","journal-title":"Proc Mach Learn Syst"},{"key":"ref249","article-title":"Learning face representation from scratch","author":"yi","year":"2014","journal-title":"arXiv 1411 7923"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32692-0_16"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37734-2_37"},{"key":"ref126","article-title":"Learning to detect malicious clients for robust federated learning","author":"li","year":"2020","journal-title":"arXiv 2002 00211"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190968"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/BigDataService52369.2021.00018"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2968399"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01564"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01057"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00115"},{"key":"ref98","article-title":"Federated auto-weighted domain adaptation","author":"jiang","year":"2023","journal-title":"arXiv 2302 05049"},{"key":"ref125","article-title":"Abnormal client behavior detection in federated learning","author":"li","year":"2019","journal-title":"arXiv 1910 09933"},{"key":"ref246","article-title":"Local–global knowledge distillation in heterogeneous federated learning with non-IID data","author":"yao","year":"2021","journal-title":"arXiv 2107 00051"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00984"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467309"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02350"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00989"},{"key":"ref255","article-title":"Multimodal federated learning via contrastive representation ensemble","author":"yu","year":"2023","journal-title":"arXiv 2302 08888"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00647"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101765"},{"key":"ref252","first-page":"12073","article-title":"Federated continual learning with weighted inter-client transfer","author":"yoon","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref94","article-title":"Sparse random networks for communication-efficient federated learning","author":"isik","year":"2022","journal-title":"arXiv 2209 15328"},{"key":"ref132","article-title":"FedBN: Federated learning on non-IID features via local batch normalization","author":"li","year":"2021","journal-title":"arXiv 2102 07623"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"ref130","article-title":"Transformer-based visual segmentation: A survey","author":"li","year":"2023","journal-title":"arXiv 2304 09854"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1145\/3460427"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01565"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00990"},{"key":"ref89","first-page":"1","article-title":"Labeled faces in the wild: A database forstudying face recognition in unconstrained environments","author":"huang","year":"2008","journal-title":"Proc Workshop Faces ‘Real-Life’ Images Detection Alignment Recognit"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1093\/gigascience\/giy065"},{"key":"ref86","first-page":"4387","article-title":"The non-IID data quagmire of decentralized machine learning","author":"hsieh","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01957"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106775"},{"key":"ref85","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref138","first-page":"2351","article-title":"Ensemble distillation for robust model fusion in federated learning","volume":"33","author":"lin","year":"2020","journal-title":"Proc NIPS"},{"key":"ref259","article-title":"Federated unsupervised representation learning","author":"zhang","year":"2020","journal-title":"arXiv 2010 08982"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_5"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00991"},{"key":"ref256","article-title":"Salvaging federated learning by local adaptation","author":"yu","year":"2020","journal-title":"arXiv 2002 04758"},{"key":"ref87","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"hsu","year":"2019","journal-title":"arXiv 1909 06335"},{"key":"ref136","article-title":"Variance reduced local SGD with lower communication complexity","author":"liang","year":"2019","journal-title":"arXiv 1912 12844"},{"key":"ref257","first-page":"7252","article-title":"Bayesian nonparametric federated learning of neural networks","author":"yurochkin","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-011-5318-8_75"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3056185"},{"key":"ref81","first-page":"1","article-title":"Class-wise adaptive self distillation for heterogeneous federated learning","volume":"22","author":"he","year":"2022","journal-title":"Proc 36th AAAI Conf Artif Intell"},{"key":"ref145","article-title":"Federated learning from only unlabeled data with class-conditional-sharing clients","author":"lu","year":"2022","journal-title":"arXiv 2204 03304"},{"key":"ref266","first-page":"1","article-title":"Character-level convolutional networks for text classification","volume":"28","author":"zhang","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref84","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00107"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS54860.2022.00094"},{"key":"ref83","article-title":"Benchmarking neural network robustness to common corruptions and surface variations","author":"hendrycks","year":"2018","journal-title":"arXiv 1807 01697"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i08.7021"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00385"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2013.12.002"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00438"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20057"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00993"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3189703"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3028011"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00384"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.87"},{"key":"ref78","article-title":"FedML: A research library and benchmark for federated machine learning","author":"he","year":"2020","journal-title":"arXiv 2007 13518"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298803"},{"key":"ref106","first-page":"1","article-title":"Pre-training without natural images","author":"kataoka","year":"2020","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2988575"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.527"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00265"},{"key":"ref75","article-title":"SODA10M: A large-scale 2D self\/semi-supervised object detection dataset for autonomous driving","author":"han","year":"2021","journal-title":"arXiv 2106 11118"},{"key":"ref104","article-title":"Mime: Mimicking centralized stochastic algorithms in federated learning","author":"karimireddy","year":"2020","journal-title":"arXiv 2008 03606"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref74","first-page":"3973","article-title":"FedBoost: A communication-efficient algorithm for federated learning","author":"hamer","year":"2020","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref105","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","author":"karimireddy","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737416"},{"key":"ref77","first-page":"1","article-title":"Escaping the big data paradigm with compact transformers","author":"hassani","year":"2021","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit Workshops (CVPRW)"},{"key":"ref102","article-title":"Memory-aware curriculum federated learning for breast cancer classification","volume":"229","author":"jim\u00e9nez-s\u00e1nchez","year":"2022","journal-title":"Comput Methods Programs Biomed"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00934"},{"key":"ref76","article-title":"Federated learning of a mixture of global and local models","author":"hanzely","year":"2020","journal-title":"arXiv 2002 05516"},{"key":"ref103","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000083","article-title":"Advances and open problems in federated learning","volume":"14","author":"kairouz","year":"2019","journal-title":"Foundations & Trends in Mach Learn"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00078"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01480"},{"key":"ref111","first-page":"18","article-title":"OpenImages: A public dataset for large-scale multi-label and multi-class image classification","volume":"2","author":"krasin","year":"2017","journal-title":"Dataset"},{"key":"ref232","first-page":"2691","article-title":"Learning from massive noisy labeled data for image classification","author":"xiao","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref70","first-page":"2066","article-title":"Geodesic flow kernel for unsupervised domain adaptation","author":"gong","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref112","author":"krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref233","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"xie","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"ref230","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"xiao","year":"2017","journal-title":"ArXiv 1708 07747"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00245"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2020190007"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2015.02.009"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00987"},{"key":"ref117","article-title":"Preservation of the global knowledge by not-true distillation in federated learning","author":"lee","year":"2021","journal-title":"arXiv 2106 03097"},{"key":"ref238","article-title":"Federated cross learning for medical image segmentation","author":"xu","year":"2022","journal-title":"arXiv 2204 02450"},{"key":"ref69","first-page":"19586","article-title":"An efficient framework for clustered federated learning","volume":"33","author":"ghosh","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref118","article-title":"Re-weighted softmax cross-entropy to control forgetting in federated learning","author":"legate","year":"2023","journal-title":"arXiv 2304 05260"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01958"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3202106"},{"key":"ref115","first-page":"3","article-title":"Tiny ImageNet visual recognition challenge","volume":"7","author":"le","year":"2015","journal-title":"CS 231N"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00779"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00994"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CBMS.2011.5999143"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2021.3076767"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.063"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599825"},{"key":"ref114","first-page":"11814","article-title":"FedScale: Benchmarking model and system performance of federated learning at scale","author":"lai","year":"2022","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01566"},{"key":"ref60","first-page":"3557","article-title":"Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach","volume":"33","author":"fallah","year":"2020","journal-title":"Proc NeurIPS Conf"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00995"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01721-8"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01563"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1145\/3558005"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981098"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00386"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.3040015"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00983"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.101992"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78618-2_4"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.534"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21743-2_17"},{"key":"ref170","article-title":"Where to begin? On the impact of pre-training and initialization in federated learning","author":"nguyen","year":"2022","journal-title":"arXiv 2206 15387"},{"key":"ref177","article-title":"Meta-heuristic as manager in federated learning approaches for image processing purposes","volume":"113","author":"po?ap","year":"2021","journal-title":"Appl Soft Comput"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01956"},{"key":"ref175","first-page":"1","article-title":"Federated adversarial domain adaptation","author":"peng","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa052911"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac9449"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20095"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101570"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01171"},{"key":"ref180","article-title":"Adaptive federated optimization","author":"reddi","year":"2020","journal-title":"arXiv 2003 00295"},{"key":"ref181","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3015958"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477558"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref187","article-title":"FEDAUX: Leveraging unlabeled auxiliary data in federated learning","author":"sattler","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.3390\/technologies10040090"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60548-3_18"},{"key":"ref182","first-page":"21554","article-title":"Robust federated learning: The case of affine distribution shifts","volume":"33","author":"reisizadeh","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref183","first-page":"169","article-title":"On data banks and privacy homomorphisms","volume":"4","author":"rivest","year":"1978","journal-title":"Found Secure Comput"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00361"},{"key":"ref269","article-title":"Federated learning with non-IID data","author":"zhao","year":"2018","journal-title":"arXiv 1806 00582"},{"key":"ref149","article-title":"FedKNOW: Federated continual learning with signature task knowledge integration at edge","author":"luopan","year":"2022","journal-title":"arXiv 2212 01738"},{"key":"ref146","article-title":"FedCLIP: Fast generalization and personalization for CLIP in federated learning","author":"lu","year":"2023","journal-title":"arXiv 2302 13485"},{"key":"ref267","article-title":"COVID-CT-dataset: A CT scan dataset about COVID-19","author":"yang","year":"2020","journal-title":"arXiv 2003 13865"},{"key":"ref147","article-title":"Real-world image datasets for federated learning","author":"luo","year":"2019","journal-title":"arXiv 1910 11089"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00387"},{"key":"ref155","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume":"54","author":"mcmahan","year":"2017","journal-title":"Proc 20th Int Conf Artif Intell Statist"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859587"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00821"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00985"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3235757"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/ICB2018.2018.00033"},{"key":"ref275","first-page":"12878","article-title":"Data-free knowledge distillation for heterogeneous federated learning","author":"zhu","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1002\/int.22818"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02351"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14676"},{"key":"ref273","first-page":"1","article-title":"Deep leakage from gradients","volume":"32","author":"zhu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1900506"},{"key":"ref271","article-title":"FedFA: Federated learning with feature anchors to align features and classifiers for heterogeneous data","author":"zhou","year":"2022","journal-title":"arXiv 2211 09299"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00777"},{"key":"ref157","article-title":"Improving federated learning face recognition via privacy-agnostic clusters","author":"meng","year":"2022","journal-title":"arXiv 2201 12467"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2014.2377694"},{"key":"ref166","article-title":"FedProc: Prototypical contrastive federated learning on non-IID data","author":"mu","year":"2021","journal-title":"arXiv 2109 12273"},{"key":"ref167","first-page":"1","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc NIPS Deep Learn Unsupervised Feature Learn Workshop"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.250"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.10.007"},{"key":"ref162","article-title":"Knowledge distillation for federated learning: A practical guide","author":"mora","year":"2022","journal-title":"arXiv 2211 04742"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2011.09.014"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00263"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3209865"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5220\/0009144704450451"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1118\/1.3528204"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2867350"},{"key":"ref14","article-title":"Federated face recognition","author":"bai","year":"2021","journal-title":"arXiv 2105 02501"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.5.4.044501"},{"key":"ref10","article-title":"Invariant risk minimization","author":"arjovsky","year":"2019","journal-title":"arXiv 1907 02893"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"ref16","first-page":"1","article-title":"A survey on deep multimodal learning for computer vision: Advances, trends, applications, and datasets","volume":"10","author":"bayoudh","year":"2021","journal-title":"Vis Comput"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.03.002"},{"key":"ref18","article-title":"FedDis: Disentangled federated learning for unsupervised brain pathology segmentation","author":"bercea","year":"2021","journal-title":"arXiv 2103 03705"},{"key":"ref2","article-title":"Federated learning based on dynamic regularization","author":"acar","year":"2021","journal-title":"arXiv 2111 04263"},{"key":"ref1","year":"2023","journal-title":"IXI Dataset - Brain Development"},{"key":"ref191","first-page":"95","article-title":"FedFR: Evaluation and selection of loss functions for federated face recognition","author":"shang","year":"2023","journal-title":"Collaborative Computing Networking Applications and Worksharing"},{"key":"ref192","first-page":"92","article-title":"Multi-institutional deep learning modeling without sharing patient data: A feasibility study on brain tumor segmentation","author":"sheller","year":"2018","journal-title":"Proc Int MICCAI Brainlesion Workshop"},{"key":"ref190","first-page":"1000","article-title":"Communication-efficient distributed optimization using an approximate Newton-type method","author":"shamir","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033395"},{"key":"ref197","first-page":"1004","article-title":"A comprehensive retinal image dataset for the assessment of glaucoma from the optic nerve head analysis","volume":"2","author":"sivaswamy","year":"2015","journal-title":"JSM Biomedical Imaging Data Papers"},{"key":"ref198","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","author":"socher","year":"2013","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02352"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2015.7447103"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00052"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00534"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10234425.pdf?arnumber=10234425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T18:22:00Z","timestamp":1696270920000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10234425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":276,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3310400","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}