{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T23:04:46Z","timestamp":1778799886283,"version":"3.51.4"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276050"],"award-info":[{"award-number":["62276050"]}],"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":["61976045"],"award-info":[{"award-number":["61976045"]}],"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":["31971288"],"award-info":[{"award-number":["31971288"]}],"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":["62131009"],"award-info":[{"award-number":["62131009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Science and Technology Program","award":["2024NSFSC0655"],"award-info":[{"award-number":["2024NSFSC0655"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tnnls.2024.3418527","type":"journal-article","created":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T13:38:55Z","timestamp":1720445935000},"page":"9636-9647","source":"Crossref","is-referenced-by-count":8,"title":["Mask-Guided Vision Transformer for Few-Shot Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4516-0895","authenticated-orcid":false,"given":"Yuzhong","family":"Chen","sequence":"first","affiliation":[{"name":"Clinical Hospital of Chengdu Brain Science Institute, MOE Key Laboratory for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8085-3520","authenticated-orcid":false,"given":"Zhenxiang","family":"Xiao","sequence":"additional","affiliation":[{"name":"Clinical Hospital of Chengdu Brain Science Institute, MOE Key Laboratory for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2938-7646","authenticated-orcid":false,"given":"Yi","family":"Pan","sequence":"additional","affiliation":[{"name":"Clinical Hospital of Chengdu Brain Science Institute, MOE Key Laboratory for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2567-627X","authenticated-orcid":false,"given":"Lin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Georgia, Athens, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0409-6129","authenticated-orcid":false,"given":"Haixing","family":"Dai","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Georgia, Athens, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Georgia, Athens, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changhe","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automation, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6075-3384","authenticated-orcid":false,"given":"Tuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Automation, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changying","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Agricultural and Biological Engineering, University of Florida, Gainesville, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6940-3911","authenticated-orcid":false,"given":"Dajiang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The University of Texas at Arlington, Arlington, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8132-9048","authenticated-orcid":false,"given":"Tianming","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Georgia, Athens, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3711-0847","authenticated-orcid":false,"given":"Xi","family":"Jiang","sequence":"additional","affiliation":[{"name":"Clinical Hospital of Chengdu Brain Science Institute, MOE Key Laboratory for Neuroinformation, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084827"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3309809"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref4","article-title":"Free lunch for few-shot learning: Distribution calibration","author":"Yang","year":"2021","journal-title":"arXiv:2101.06395"},{"key":"ref5","article-title":"Budget-aware few-shot learning via graph convolutional network","author":"Yan","year":"2022","journal-title":"arXiv:2201.02304"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00931"},{"key":"ref8","article-title":"Revisiting fine-tuning for few-shot learning","author":"Nakamura","year":"2019","journal-title":"arXiv:1910.00216"},{"key":"ref9","article-title":"Frustratingly simple few-shot object detection","author":"Wang","year":"2020","journal-title":"arXiv:2003.06957"},{"key":"ref10","article-title":"Cross-domain few-shot learning with meta fine-tuning","author":"Cai","year":"2020","journal-title":"arXiv:2005.10544"},{"key":"ref11","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3227717"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993277"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3133268"},{"key":"ref17","article-title":"Learning active learning from data","author":"Konyushkova","year":"2017","journal-title":"arXiv:1703.03365"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref21","article-title":"LocalViT: Bringing locality to vision transformers","author":"Li","year":"2021","journal-title":"arXiv:2104.05707"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20252"},{"key":"ref23","article-title":"When vision transformers outperform ResNets without pre-training or strong data augmentations","author":"Chen","year":"2021","journal-title":"arXiv:2106.01548"},{"key":"ref24","article-title":"Escaping the big data paradigm with compact transformers","author":"Hassani","year":"2021","journal-title":"arXiv:2104.05704"},{"key":"ref25","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2021","journal-title":"arXiv:2111.06377"},{"key":"ref26","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref27","article-title":"BEiT v2: Masked image modeling with vector-quantized visual tokenizers","author":"Peng","year":"2022","journal-title":"arXiv:2208.06366"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/513"},{"key":"ref29","article-title":"Meta-learning: A survey","author":"Vanschoren","year":"2018","journal-title":"arXiv:1810.03548"},{"key":"ref30","article-title":"A universal representation transformer layer for few-shot image classification","author":"Liu","year":"2020","journal-title":"arXiv:2006.11702"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-90196-7_6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3700-8"},{"key":"ref33","article-title":"You only look at one sequence: Rethinking transformer in vision through object detection","author":"Fang","year":"2021","journal-title":"arXiv:2106.00666"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","article-title":"Patch slimming for efficient vision transformers","author":"Tang","year":"2021","journal-title":"arXiv:2106.02852"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027314"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.01.019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.9"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_35"},{"key":"ref41","first-page":"1","article-title":"Deep learning on a data diet: Finding important examples early in training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Paul"},{"key":"ref42","article-title":"Deep learning for anomaly detection: A survey","author":"Chalapathy","year":"2019","journal-title":"arXiv:1901.03407"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995740"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref45","article-title":"Hierarchical semantic tree concept whitening for interpretable image classification","author":"Dai","year":"2023","journal-title":"arXiv:2307.04343"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.42"},{"key":"ref47","first-page":"1","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Vinyals"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref49","article-title":"Meta-learning with differentiable closed-form solvers","author":"Bertinetto","year":"2018","journal-title":"arXiv:1805.08136"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"issue":"1","key":"ref51","first-page":"1","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. CVPR","volume":"2","author":"Khosla"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21699"},{"key":"ref55","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1093\/psyrad\/kkad033"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1093\/psyrad\/kkad011"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/10982361\/10589307.pdf?arnumber=10589307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:53Z","timestamp":1764959993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10589307\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":60,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3418527","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}