{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T17:06:56Z","timestamp":1774026416394,"version":"3.50.1"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"crossref","award":["2019YFF0303300"],"award-info":[{"award-number":["2019YFF0303300"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"crossref","award":["2019YFF0303302"],"award-info":[{"award-number":["2019YFF0303302"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"crossref","award":["2018YFB2100500"],"award-info":[{"award-number":["2018YFB2100500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906080"],"award-info":[{"award-number":["61906080"]}],"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":["61763028"],"award-info":[{"award-number":["61763028"]}],"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":["61773071"],"award-info":[{"award-number":["61773071"]}],"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":["61922015"],"award-info":[{"award-number":["61922015"]}],"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":["U19B2036"],"award-info":[{"award-number":["U19B2036"]}],"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":["61976138"],"award-info":[{"award-number":["61976138"]}],"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":["61977047"],"award-info":[{"award-number":["61977047"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003711","name":"National Science and Technology Major Program of the Ministry of Science and Technology","doi-asserted-by":"publisher","award":["2018ZX03001031"],"award-info":[{"award-number":["2018ZX03001031"]}],"id":[{"id":"10.13039\/501100003711","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Academy of Artificial Intelligence","award":["BAAI2020ZJ0204"],"award-info":[{"award-number":["BAAI2020ZJ0204"]}]},{"name":"Beijing Nova Programme Interdisciplinary Cooperation Project","award":["Z191100001119140"],"award-info":[{"award-number":["Z191100001119140"]}]},{"DOI":"10.13039\/501100004826","name":"Key Program of Beijing Municipal Natural Science Foundation","doi-asserted-by":"publisher","award":["L172030"],"award-info":[{"award-number":["L172030"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008536","name":"Hong-liu Outstanding Youth Talents Foundation of Lanzhou University of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008536","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010098","name":"Shanghai Science and Technology Committee","doi-asserted-by":"publisher","award":["2015F0203-000-06"],"award-info":[{"award-number":["2015F0203-000-06"]}],"id":[{"id":"10.13039\/100010098","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003395","name":"Shanghai Municipal Education Commission","doi-asserted-by":"publisher","award":["2019-01-07-00-01-E00003"],"award-info":[{"award-number":["2019-01-07-00-01-E00003"]}],"id":[{"id":"10.13039\/501100003395","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BUPT Excellent Ph.D. Students Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/tip.2020.2990277","type":"journal-article","created":{"date-parts":[[2020,5,6]],"date-time":"2020-05-06T20:10:44Z","timestamp":1588795844000},"page":"6482-6495","source":"Crossref","is-referenced-by-count":41,"title":["OSLNet: Deep Small-Sample Classification With an Orthogonal Softmax Layer"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8833-9401","authenticated-orcid":false,"given":"Xiaoxu","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4081-3001","authenticated-orcid":false,"given":"Dongliang","family":"Chang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2950-2488","authenticated-orcid":false,"given":"Zhanyu","family":"Ma","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6856-8928","authenticated-orcid":false,"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1174-610X","authenticated-orcid":false,"given":"Jing-Hao","family":"Xue","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Jingyi","family":"Yu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9045-1339","authenticated-orcid":false,"given":"Jun","family":"Guo","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00501"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00089"},{"key":"ref70","first-page":"4261","article-title":"Can we gain more from orthogonality regularizations in training deep networks?","author":"bansal","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408872"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref74","author":"mohri","year":"2012","journal-title":"Foundations of Machine Learning"},{"key":"ref39","first-page":"7115","article-title":"Tapnet: Neural network augmented with task-adaptive projection for few-shot learning","author":"yoon","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref75","first-page":"463","article-title":"Rademacher and Gaussian complexities: Risk bounds and structural results","volume":"3","author":"bartlett","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.083"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref79","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref33","first-page":"5334","article-title":"Generalizing to unseen domains via adversarial data augmentation","author":"volpi","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref31","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"hinton","year":"2012","journal-title":"arXiv 1207 0580"},{"key":"ref30","first-page":"1946","article-title":"Virtual class enhanced discriminative embedding learning","author":"chen","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","first-page":"3567","article-title":"Data programming: Creating large training sets, quickly","author":"ratner","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.241"},{"key":"ref35","first-page":"3236","article-title":"Learning to compose domain-specific transformations for data augmentation","author":"ratner","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","first-page":"2539","article-title":"Deep convolutional inverse graphics network","author":"kulkarni","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref60","first-page":"351","article-title":"Dropout training as adaptive regularization","author":"wager","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref62","first-page":"6222","article-title":"Learning towards minimum hyperspherical energy","author":"liu","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref61","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","author":"wan","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref63","first-page":"3950","article-title":"Deep hyperspherical learning","author":"liu","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","first-page":"507","article-title":"Large-margin softmax loss for convolutional neural networks","author":"liu","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref64","first-page":"1120","article-title":"Unitary evolution recurrent neural networks","author":"arjovsky","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","first-page":"1","article-title":"Snapshot ensembles: Train 1, get M for free","author":"huang","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref65","first-page":"1","article-title":"Orthogonal weight normalization: Solution to optimization over multiple dependent stiefel manifolds in deep neural networks","author":"huang","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.539"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2973812"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.410"},{"key":"ref68","first-page":"1485","article-title":"Hyperspherical prototype networks","author":"mettes","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref69","first-page":"1","article-title":"Regularizing CNNs with locally constrained decorrelations","author":"rodr\u00edguez","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref20","first-page":"1","article-title":"A closer look at few-shot classification","author":"chen","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2750404"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00049"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2874313"},{"key":"ref23","article-title":"The effectiveness of data augmentation in image classification using deep learning","author":"perez","year":"2017","journal-title":"arXiv 1712 04621"},{"key":"ref26","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2899972"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00950"},{"key":"ref51","first-page":"499","article-title":"A discriminative feature learning approach for deep face recognition","author":"wen","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1137\/S0036144597321909"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2016.2635663"},{"key":"ref57","first-page":"1","article-title":"Temporal ensembling for semi-supervised learning","author":"laine","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref56","first-page":"28","article-title":"Swapout: Learning an ensemble of deep architectures","author":"singh","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref55","first-page":"67","article-title":"The use of the ambiguity decomposition in neural network ensemble learning methods","author":"brown","year":"2003","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2004.09.006"},{"key":"ref53","first-page":"8778","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","author":"zhang","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_8"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2924811"},{"key":"ref40","first-page":"3320","article-title":"How transferable are features in deep neural networks?","author":"yosinski","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2408354"},{"key":"ref13","article-title":"One-shot learning with memory-augmented neural networks","author":"santoro","year":"2016","journal-title":"arXiv 1605 06065"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2819503"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2895651"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.3102\/10769986022003349"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2737007"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-2766-4_12"},{"key":"ref17","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref84","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref18","first-page":"1","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref83","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2615921"},{"key":"ref80","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2016","journal-title":"arXiv 1608 03983"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2844853"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.57"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"ref5","first-page":"4077","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref8","article-title":"Small sample learning in big data era","author":"shu","year":"2018","journal-title":"arXiv 1808 04572"},{"key":"ref7","first-page":"3630","article-title":"Matching networks for one shot learning","author":"vinyals","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.02.099"},{"key":"ref46","first-page":"2208","article-title":"Deep transfer learning with joint adaptation networks","author":"long","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.222"},{"key":"ref48","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.100"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2643667"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"jialin pan","year":"2010","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00456"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/8835130\/09088302.pdf?arnumber=9088302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:13Z","timestamp":1651070353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9088302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/tip.2020.2990277","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}