{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T16:56:25Z","timestamp":1775235385293,"version":"3.50.1"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,3,1]]},"DOI":"10.1109\/tpami.2020.3018506","type":"journal-article","created":{"date-parts":[[2020,8,21]],"date-time":"2020-08-21T20:17:38Z","timestamp":1598041058000},"page":"1443-1456","source":"Crossref","is-referenced-by-count":98,"title":["Meta-Transfer Learning Through Hard Tasks"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2689-317X","authenticated-orcid":false,"given":"Qianru","family":"Sun","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5316-3028","authenticated-orcid":false,"given":"Yaoyao","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1260-5635","authenticated-orcid":false,"given":"Zhaozheng","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9683-5237","authenticated-orcid":false,"given":"Bernt","family":"Schiele","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"issue":"7553","key":"ref1","article-title":"Deep learning","volume":"521","author":"Yann","year":"2015","journal-title":"Nature"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"ref5","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00049"},{"key":"ref7","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Clevert"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01164-6"},{"key":"ref9","article-title":"Generative adversarial residual pairwise networks for one shot learning","author":"Mehrotra","year":"2017"},{"key":"ref10","first-page":"2850","article-title":"Delta-encoder: An effective sample synthesis method for few-shot object recognition","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Schwartz"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00760"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01052"},{"key":"ref13","first-page":"670","article-title":"Few-shot generative modelling with generative matching networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Bartunov"},{"key":"ref14","first-page":"6","article-title":"On the optimization of a synaptic learning rule","volume-title":"Optimality in Artificial and Biological Neural Networks","author":"Bengio","year":"1992"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1992.287172"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_1"},{"key":"ref17","first-page":"9537","article-title":"Probabilistic model-agnostic meta-learning","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Finn"},{"key":"ref18","article-title":"Recasting gradient-based meta-learning as hierarchical bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Grant"},{"key":"ref19","first-page":"1563","article-title":"Bilevel programming for hyperparameter optimization and meta-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Franceschi"},{"key":"ref20","first-page":"2933","article-title":"Gradient-based meta-learning with learned layerwise metric and subspace","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.14711\/thesis-991012636368103412"},{"key":"ref22","article-title":"How to train your MAML","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Antoniou"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"ref24","article-title":"Empirical bayes meta-learning with synthetic gradients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref25","article-title":"Meta-learning with latent embedding optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rusu"},{"key":"ref26","article-title":"Meta-learning for semi-supervised few-shot classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren"},{"key":"ref27","first-page":"10 276","article-title":"Learning to self-train for semi-supervised few-shot classification","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref28","first-page":"3630","article-title":"Matching networks for one shot learning","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref29","first-page":"2554","article-title":"Meta networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Munkhdalai"},{"key":"ref30","article-title":"Meta-sgd: Learning to learn quickly for few shot learning","author":"Li","year":"2017"},{"key":"ref31","first-page":"6467","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lopez-Paz and"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60536-8"},{"key":"ref33","first-page":"4077","article-title":"Prototypical networks for few-shot learning","author":"Snell","year":"2017","journal-title":"Int. Conf. Neural Inf. Process. Syst."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref37","first-page":"719","article-title":"TADAM: Task dependent adaptive metric for improved few-shot learning","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Oreshkin"},{"key":"ref38","first-page":"177","article-title":"Using fast weights to deblur old memories","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Geoffrey"},{"key":"ref39","article-title":"Optimization as a model for few-shot learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravi"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"ref42","first-page":"4005","article-title":"Cross attention network for few-shot classification","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Hou"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00382"},{"key":"ref44","article-title":"Cross-modulation networks for few-shot learning","author":"Prol","year":"2018"},{"key":"ref45","article-title":"A closer look at few-shot classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref46","article-title":"Meta-learning with differentiable closed-form solvers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bertinetto"},{"key":"ref47","article-title":"Few-shot learning with graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Satorras"},{"key":"ref48","article-title":"Learning to propagate labels: Transductive propagation network for few-shot learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref49","first-page":"3825","article-title":"Lgm-net: Learning to generate matching networks for few-shot learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref50","article-title":"Snail: A simple neural attentive meta-learner","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mishra"},{"key":"ref51","article-title":"Discriminative k-shot learning using probabilistic models","author":"Bauer","year":"2017"},{"key":"ref52","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Santoro"},{"key":"ref53","first-page":"2933","article-title":"Gradient-based meta-learning with learned layerwise metric and subspace","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2091281"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2007.37"},{"key":"ref56","first-page":"5085","article-title":"Transfer learning via learning to transfer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wei"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.54"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01226"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref61","first-page":"625","article-title":"Why does unsupervised pre-training help deep learning?","volume":"11","author":"Erhan","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.351"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref65","first-page":"46","article-title":"Transfer learning in a transductive setting","volume-title":"Proc. 26th Int. Conf. Neural Inf. Process. Syst.","author":"Rohrbach"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00974"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00755"},{"key":"ref68","first-page":"76","article-title":"Adapted deep embeddings: A synthesis of methods for k-shot inductive transfer learning","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Scott"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.306"},{"key":"ref70","first-page":"5235","article-title":"Curriculum learning by transfer learning: Theory and experiments with deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Weinshall"},{"key":"ref71","first-page":"1311","article-title":"Automated curriculum learning for neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Graves"},{"key":"ref72","first-page":"1189","article-title":"Self-paced learning for latent variable models","volume-title":"Proc. 23rd Int. Conf. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299188"},{"key":"ref74","first-page":"2309","article-title":"Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.554"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.307"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref78","first-page":"3661","article-title":"Rapid adaptation with conditionally shifted neurons","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Munkhdalai"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref80","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s13398-014-0173-7.2"},{"key":"ref83","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9703108\/09173698.pdf?arnumber=9173698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:27:15Z","timestamp":1704842835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9173698\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,1]]},"references-count":83,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.3018506","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":[[2022,3,1]]}}}