{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:49:21Z","timestamp":1774964961313,"version":"3.50.1"},"reference-count":75,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T00:00:00Z","timestamp":1695600000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T00:00:00Z","timestamp":1695600000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,25]]},"DOI":"10.1109\/hpec58863.2023.10363479","type":"proceedings-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:39:57Z","timestamp":1703533197000},"page":"1-13","source":"Crossref","is-referenced-by-count":1,"title":["Contextualizing Enhances Gradient Based Meta Learning for Few Shot Image Classification"],"prefix":"10.1109","author":[{"given":"Evan","family":"Vogelbaum","sequence":"first","affiliation":[{"name":"MIT EECS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rumen","family":"Dangovski","sequence":"additional","affiliation":[{"name":"MIT EECS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Jing","sequence":"additional","affiliation":[{"name":"MIT Physics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marin","family":"Soljacic","sequence":"additional","affiliation":[{"name":"MIT Physics"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Imagenet classification with deep convolutional neural networks","year":"2012","journal-title":"NeurIPS"},{"key":"ref2","volume-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022"},{"key":"ref3","article-title":"How to train your MAML","volume-title":"ICLR","author":"Antoniou","year":"2019"},{"key":"ref4","article-title":"Layer normalization","volume-title":"NeurIPS 2016 Deep Learning Symposium","author":"Lei Ba","year":"2016"},{"key":"ref5","article-title":"Alpha MAML: adaptive model-agnostic meta-learning","volume-title":"ICML workshop","author":"Singh Behl","year":"2019"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Sparks of artificial general intelligence: Early experiments with gpt-4","author":"Bubeck","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.376"},{"key":"ref9","article-title":"Few-shot learning with meta metric learners","volume-title":"NeurIPS workshop","author":"Cheng","year":"2017"},{"key":"ref10","article-title":"Palm: Scaling language modeling with pathways","author":"Chowdhery","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"MetaInit: Initializing learning by learning to initialize","author":"Dauphin","year":"2019","journal-title":"NeurIPS"},{"key":"ref12","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"International Conference on Machine Learning","author":"Dehghani","year":"2023"},{"key":"ref13","author":"Dosovitskiy","year":"2021","journal-title":"An image is worth 16x16 words: Transformers for image recognition at scale"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_45"},{"key":"ref15","article-title":"Meta-learning and universality: Deep representations and gradient descent can approximate any learning algorithm","author":"Finn","year":"2018","journal-title":"ICLR"},{"key":"ref16","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017","journal-title":"ICML"},{"key":"ref17","article-title":"Meta-learning with warped gradient descent","volume-title":"International Conference on Learning Representations","author":"Flennerhag","year":"2020"},{"key":"ref18","article-title":"Meta learning shared hierarchies","author":"Frans","year":"2018","journal-title":"ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_17"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00459"},{"key":"ref21","author":"Gidaris","year":"2020","journal-title":"Online bag-of-visual-words generation for unsupervised representation learning"},{"key":"ref22","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"Glorot","year":"2010","journal-title":"AISTATS"},{"key":"ref23","article-title":"Meta-learning probabilistic inference for prediction","author":"Gordon","year":"2019","journal-title":"ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.09.116"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref26","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01199"},{"key":"ref28","article-title":"Transferable meta learning across domains","author":"Kang","year":"2018","journal-title":"UAl"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00534"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref31","article-title":"Siamese neural networks for one-shot image recognition","volume-title":"ICML workshop","author":"Koch","year":"2015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab3050"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01091"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00743"},{"key":"ref36","article-title":"Meta-sgd: Learning to learn quickly for few shot learning","author":"Li","year":"2017","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00948"},{"key":"ref38","author":"Maji","year":"2013","journal-title":"Fine-grained visual classification of aircraft"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.47"},{"key":"ref40","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"TADAM: task dependent adaptive metric for improved few-shot learning","author":"Oreshkin","year":"2018","journal-title":"NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00103"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"issue":"8","key":"ref44","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref45","article-title":"Rapid learning or feature reuse? towards understanding the effectiveness of maml","author":"Raghu","year":"2020","journal-title":"ICLR"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2861573"},{"key":"ref47","article-title":"Optimization as a model for few-shot learning","author":"Ravi","year":"2017","journal-title":"ICLR"},{"key":"ref48","article-title":"Meta-learning for semi-supervised few-shot classification","author":"Ren","year":"2018","journal-title":"ICLR"},{"key":"ref49","article-title":"e supercomputing on 40,000 cores for machine learning and data analysis","author":"Reuther","year":"2018","journal-title":"HPEC"},{"key":"ref50","article-title":"Learning to learn without forgetting by maximizing transfer and minimizing interference","author":"Riemer","year":"2019","journal-title":"ICLR"},{"key":"ref51","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"ICLR"},{"key":"ref52","article-title":"Prototypical networks for few-shot learning","author":"Snell","year":"2017","journal-title":"NeurIPS"},{"key":"ref53","article-title":"Prototypical networks for few-shot learning","author":"Snell","year":"2017","journal-title":"NIPS"},{"key":"ref54","article-title":"Improved deep metric learning with multi-class n-pair loss objective","author":"Sohn","year":"2016","journal-title":"NeurIPS"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"ref56","article-title":"ES-MAML: Simple hessian-free meta learning","author":"Song","year":"2019","journal-title":"ICLR"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00049"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"ref61","author":"Touvron","year":"2021","journal-title":"Training data-efficient image transformers & distillation through attention"},{"key":"ref62","article-title":"Few-shot learning through an information retrieval lens","author":"Triantafillou","year":"2017","journal-title":"NeurIPS"},{"key":"ref63","article-title":"Meta-dataset: A dataset of datasets for learning to learn from few examples","author":"Triantafillou","year":"2020","journal-title":"ICLR"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_2"},{"key":"ref65","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref66","article-title":"Matching networks for one shot learning","author":"Vinyals","year":"2016","journal-title":"NeurIPS"},{"key":"ref67","author":"Vogelbaum","year":"2020","journal-title":"Contextualizing enhances gradient based meta learning"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.283"},{"key":"ref69","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"arXiv preprint"},{"key":"ref70","article-title":"Learned optimizers that scale and generalize","author":"Wichrowska","year":"2017","journal-title":"ICLR"},{"key":"ref71","article-title":"Meta-gradient reinforcement learning","author":"Xu","year":"2018","journal-title":"NeurIPS"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"ref73","article-title":"Meta-learning without memorization","author":"Yin","year":"2020","journal-title":"ICLR"},{"key":"ref74","article-title":"Bayesian model-Algorithm 1 ProtoContext: Head Contextualizations Training Step for one Inner Loop Step. PyTorch-like Pseudocode. agnostic meta-learning","author":"Yoon","year":"2018","journal-title":"NeurIPS"},{"key":"ref75","article-title":"Fast context adaptation via meta-learning","author":"Zintgraf","year":"2019","journal-title":"ICML"}],"event":{"name":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","location":"Boston, MA, USA","start":{"date-parts":[[2023,9,25]]},"end":{"date-parts":[[2023,9,29]]}},"container-title":["2023 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10363430\/10363422\/10363479.pdf?arnumber=10363479","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T20:30:03Z","timestamp":1705091403000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10363479\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,25]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/hpec58863.2023.10363479","relation":{},"subject":[],"published":{"date-parts":[[2023,9,25]]}}}