{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T07:58:05Z","timestamp":1781164685736,"version":"3.54.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"EPSRC Centre for Doctoral Training in Robotics and Autonomous Systems"},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/S515061\/1"],"award-info":[{"award-number":["EP\/S515061\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SeeByte Ltd, Edinburgh, U.K."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tai.2023.3298303","type":"journal-article","created":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T14:02:19Z","timestamp":1690207339000},"page":"1348-1358","source":"Crossref","is-referenced-by-count":41,"title":["Few-Shot Learning With Class Imbalance"],"prefix":"10.1109","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3799-5921","authenticated-orcid":false,"given":"Mateusz","family":"Ochal","sequence":"first","affiliation":[{"name":"School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9500-6899","authenticated-orcid":false,"given":"Massimiliano","family":"Patacchiola","sequence":"additional","affiliation":[{"name":"School of Informatics, University of Edinburgh, Edinburgh, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6538-4039","authenticated-orcid":false,"given":"Jose","family":"Vazquez","sequence":"additional","affiliation":[{"name":"SeeByte Ltd., Edinburgh, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8100-506X","authenticated-orcid":false,"given":"Amos","family":"Storkey","sequence":"additional","affiliation":[{"name":"School of Informatics, University of Edinburgh, Edinburgh, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1537-8834","authenticated-orcid":false,"given":"Sen","family":"Wang","sequence":"additional","affiliation":[{"name":"I-X & the Department of Electrical and Electronic Engineering, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"How sensitive are meta-learners to dataset imbalance?","author":"ochal","year":"0","journal-title":"Proc Int Conf Learn Representations Workshop Learn"},{"key":"ref57","article-title":"How to train your MAMLL","author":"antoniou","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995720"},{"key":"ref56","article-title":"Assume, augment and learn: Unsupervised few-shot meta-learning via random labels and data augmentation","author":"antoniou","year":"2019"},{"key":"ref15","article-title":"Federated meta-learning with fast convergence and efficient communication","author":"chen","year":"2018"},{"key":"ref59","first-page":"90","article-title":"Learning to transfer learn","author":"cheng","year":"0","journal-title":"Proc ACM Multimedia Conf Multimedia Conf"},{"key":"ref14","first-page":"1920","article-title":"Online meta-learning","author":"finn","year":"0","journal-title":"Mach Learn Res"},{"key":"ref58","first-page":"1","article-title":"Why resampling outperforms reweighting for correcting sampling bias with stochastic gradients","author":"an","year":"0","journal-title":"Proc Int Conf Learn Repretations"},{"key":"ref53","first-page":"9290","article-title":"Realistic evaluation of transductive few-shot learning","volume":"34","author":"veilleux","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref52","article-title":"SimpleShot: Revisiting nearest-neighbor classification for few-shot learning","author":"wang","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"ref55","first-page":"8151","article-title":"Data augmentation for meta-learning","author":"ni","year":"0","journal-title":"Proc Adv Neural Inf Process Syst Workshop Meta-Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-2002-6504"},{"key":"ref54","first-page":"5705","article-title":"Meta-learning requires meta-augmentation","author":"rajendran","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533550"},{"key":"ref16","first-page":"1","article-title":"Meta-dataset: A dataset of datasets for learning to learn from few examples","author":"triantafillou","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref19","first-page":"1","article-title":"Learning to balance: Bayesian meta-learning for imbalanced and out-of-distribution tasks","author":"lee","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2014.2345380"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00782"},{"key":"ref46","article-title":"Metabalance: High-performance neural networks for class-imbalanced data","author":"bansal","year":"2022","journal-title":"openreview"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00981"},{"key":"ref48","first-page":"1","article-title":"A theoretical analysis of the number of shots in few-shot learning","author":"cao","year":"0","journal-title":"Proc Int Conf Learn Repretations"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08262-0"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00459"},{"key":"ref41","article-title":"Incremental few-shot learning with attention attractor networks","volume":"32","author":"ren","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00166"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.328"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00882"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-018-0151-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.011"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.2995703"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052900"},{"key":"ref6","article-title":"Matching networks for one shot learning","author":"vinyals","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01064"},{"key":"ref40","first-page":"2445","article-title":"Information maximization for few-shot learning","volume":"33","author":"boudiaf","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref35","first-page":"1","article-title":"A baseline for few-shot image classification","author":"dhillon","year":"0","journal-title":"Proc Int Conf Learn Repretations"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_58"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00069"},{"key":"ref36","first-page":"16108","article-title":"Bayesian meta-learning in the few-shot setting via deep kernels","author":"patacchiola","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","first-page":"1","article-title":"Towards a neural statistician","author":"edwards","year":"0","journal-title":"Proc Int Conf Learn Repretations"},{"key":"ref33","first-page":"1","article-title":"MetaGAN: An adversarial approach to few-shot learning","author":"zhang","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref32","first-page":"1","article-title":"Optimization as a model for few-shot learning","author":"ravi","year":"0","journal-title":"Proc Int Conf Learn Repretations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF38699.2020.9389475"},{"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":"ref39","first-page":"1","article-title":"Learning to propagate labels: Transductive propagation network for few-shot learning","author":"liu","year":"0","journal-title":"Proc Int Conf Learn Repretations"},{"key":"ref38","article-title":"Learning to learn by self-critique","volume":"32","author":"antoniou","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref24","first-page":"1","article-title":"A closer look at few-shot classification","author":"chen","year":"0","journal-title":"Proc Int Conf Learn Repretations"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-1765(01)00524-9"},{"key":"ref67","article-title":"A maximum log-likelihood method for imbalanced few-shot learning tasks","author":"hess","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref20","first-page":"1520","article-title":"Learning to stop while learning to predict","author":"chen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref64","article-title":"Bayesian few-shot classification with one-vs-each pólya-gamma augmented Gaussian processes","author":"snell","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref63","article-title":"Defining benchmarks for continual few-shot learning","author":"antoniou","year":"0","journal-title":"Proc NeurIPS MetaLearn 2020 Workshop on Meta-Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0192-5"},{"key":"ref66","first-page":"1","article-title":"Bayesian model-agnostic meta-learning","author":"yoon","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00672"},{"key":"ref65","article-title":"Contextualizing enhances gradient based meta learning","author":"vogelbaum","year":"2020"},{"key":"ref28","first-page":"1","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.05.004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref60","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref62","article-title":"Meta-: Learning to Learn Quickly for Few-Shot Learning","author":"li","year":"2017"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10261321\/10192558.pdf?arnumber=10192558","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:08:44Z","timestamp":1755911324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10192558\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":67,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tai.2023.3298303","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}