{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:28:16Z","timestamp":1768073296708,"version":"3.49.0"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Career Development Fund","award":["C210812045"],"award-info":[{"award-number":["C210812045"]}]},{"name":"A*STAR Singapore"},{"name":"PNRR MUR"},{"name":"Future Artificial Intelligence Research"},{"name":"European Union - NextGenerationEU"},{"DOI":"10.13039\/501100000288","name":"Royal Society","doi-asserted-by":"publisher","award":["SPREM RGS-R1-201149"],"award-info":[{"award-number":["SPREM RGS-R1-201149"]}],"id":[{"id":"10.13039\/501100000288","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Amazon Research Award"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tpami.2023.3328184","type":"journal-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T17:52:55Z","timestamp":1698429175000},"page":"1996-2010","source":"Crossref","is-referenced-by-count":4,"title":["Robust Meta-Representation Learning via Global Label Inference and Classification"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5208-4555","authenticated-orcid":false,"given":"Ruohan","family":"Wang","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup>R), Agency for Science, Technology and Research (A*STAR), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6616-0045","authenticated-orcid":false,"given":"John Isak Texas","family":"Falk","sequence":"additional","affiliation":[{"name":"Centre for Artificial Intelligence, Computer Science Department, University College London, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9415-098X","authenticated-orcid":false,"given":"Massimiliano","family":"Pontil","sequence":"additional","affiliation":[{"name":"Centre for Artificial Intelligence, Computer Science Department, University College London, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0249-5273","authenticated-orcid":false,"given":"Carlo","family":"Ciliberto","sequence":"additional","affiliation":[{"name":"Centre for Artificial Intelligence, Computer Science Department, University College London, London, U.K."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00881"},{"key":"ref2","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref3","first-page":"136","article-title":"OptNet: Differentiable optimization as a layer in neural networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Amos"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01450"},{"key":"ref5","article-title":"Beyond simple meta-learning: Multi-purpose models for multi-domain, active and continual few-shot learning","author":"Bateni","year":"2022"},{"key":"ref6","article-title":"Meta-learning with differentiable closed-form solvers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bertinetto"},{"key":"ref7","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref8","article-title":"A closer look at few-shot classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00893"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref11","first-page":"964","article-title":"The advantage of conditional meta-learning for biased regularization and fine-tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Denevi"},{"key":"ref12","first-page":"253","article-title":"Conditional meta-learning of linear representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Denevi"},{"key":"ref13","article-title":"Few-shot learning via learning the representation, provably","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Du"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_45"},{"key":"ref15","first-page":"80","article-title":"Lessons learned from the neurips 2021 metadl challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Competitions Demonstrations Track","author":"El Baz"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"ref17","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":"ref18","first-page":"1568","article-title":"Bilevel programming for hyperparameter optimization and meta-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Franceschi"},{"key":"ref19","first-page":"10750","article-title":"Dropblock: A regularization method for convolutional networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ghiasi"},{"key":"ref20","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gidaris"},{"key":"ref21","first-page":"3607","article-title":"Unraveling meta-learning: Understanding feature representations for few-shot tasks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goldblum"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaz007"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1142\/9781860949739_0006"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3079209"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2013.6706807"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2007.55"},{"key":"ref30","first-page":"9119","article-title":"Reconciling meta-learning and continual learning with online mixtures of tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jerfel"},{"key":"ref31","article-title":"Learning to learn with conditional class dependencies","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jiang"},{"key":"ref32","article-title":"The quick, draw!-AI experiment","author":"Jongejan","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab3050"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00939"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00702"},{"key":"ref39","article-title":"Meta-SGD: Learning to learn quickly for few-shot learning","author":"Li","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref41","article-title":"A universal representation transformer layer for few-shot image classification","author":"Liu","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref43","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref44","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093338"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref48","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref50","first-page":"721","article-title":"TADAM: Task dependent adaptive metric for improved few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Oreshkin"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00610"},{"key":"ref54","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref55","article-title":"Rapid learning or feature reuse? Towards understanding the effectiveness of maml","author":"Raghu","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00042"},{"key":"ref57","article-title":"Meta-learning for semi-supervised few-shot classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren"},{"key":"ref58","first-page":"7959","article-title":"Fast and flexible multi-task classification using conditional neural adaptive processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Requeima"},{"key":"ref59","article-title":"ImageNet-21 k pretraining for the masses","author":"Ridnik","year":"2021"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_8"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref62","article-title":"Meta-learning with latent embedding optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rusu"},{"key":"ref63","article-title":"Optimized generic feature learning for few-shot classification across domains","author":"Saikia","year":"2020"},{"key":"ref64","article-title":"FGVCx fungi classification challenge","author":"Schroeder","year":"2018"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"ref66","article-title":"FIT: Parameter efficient few-shot transfer learning for personalized and federated image classification","author":"Shysheya","year":"2022"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00049"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"ref72","article-title":"Meta-dataset: A dataset of datasets for learning to learn from few examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Triantafillou"},{"key":"ref73","first-page":"10424","article-title":"Learning a universal template for few-shot dataset generalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Triantafillou"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_2"},{"key":"ref75","first-page":"3637","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref76","first-page":"1","article-title":"Multimodal model-agnostic meta-learning via task-aware modulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vuorio"},{"key":"ref77","first-page":"2587","article-title":"Structured prediction for conditional meta-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref78","first-page":"27160","article-title":"The role of global labels in few-shot classification and how to infer them","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref79","article-title":"Caltech-UCSD birds 200","author":"Welinder","year":"2010"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00792"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00880"},{"key":"ref82","article-title":"Free lunch for few-shot learning: Distribution calibration","author":"Yang","year":"2021"},{"key":"ref83","first-page":"7045","article-title":"Hierarchically structured meta-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yao"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01222"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10461350\/10298810.pdf?arnumber=10298810","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T02:21:47Z","timestamp":1709864507000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10298810\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":85,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3328184","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":[[2024,4]]}}}