{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T16:37:39Z","timestamp":1745944659053,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"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":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412047","type":"proceedings-article","created":{"date-parts":[[2021,5,6]],"date-time":"2021-05-06T02:15:54Z","timestamp":1620267354000},"page":"150-157","source":"Crossref","is-referenced-by-count":3,"title":["Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning?"],"prefix":"10.1109","author":[{"given":"Xiang","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongfei Mark","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"journal-title":"MNIST Handwritten Digit Database","year":"2010","author":"lecun","key":"ref38"},{"journal-title":"How to train your maml","year":"2018","author":"antoniou","key":"ref33"},{"journal-title":"Online learning rate adaptation with hypergradient descent","year":"2017","author":"baydin","key":"ref32"},{"journal-title":"Alpha maml Adaptive model- agnostic meta-learning","year":"2019","author":"behl","key":"ref31"},{"key":"ref30","article-title":"Learning to generalize: Meta-learning for domain generalization","author":"li","year":"0","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"journal-title":"Adam A method for stochastic optimization","year":"2014","author":"kingma","key":"ref37"},{"key":"ref36","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition","year":"2014","author":"simonyan","key":"ref35"},{"key":"ref34","article-title":"Enhancing generalization of first-order meta-learning","author":"jayathilaka","year":"0","journal-title":"In International Conference on Learning Representations Workshop"},{"key":"ref10","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"journal-title":"Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift","year":"2015","author":"ioffe","key":"ref11"},{"key":"ref12","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"0","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70 JMLR org"},{"key":"ref13","first-page":"3981","article-title":"Learning to learn by gradient descent by gradient descent","author":"andrychowicz","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009","journal-title":"Citeseer Tech Rep"},{"key":"ref15","first-page":"5947","article-title":"Exploring generalization in deep learning","author":"neyshabur","year":"2017","journal-title":"Advances in neural information processing systems"},{"journal-title":"Sensitivity and Generalization in Neural Networks an Empirical Study","year":"2018","author":"novak","key":"ref16"},{"journal-title":"Understanding training and generalization in deep learning by Fourier analysis","year":"2018","author":"xu","key":"ref17"},{"journal-title":"Training behavior of deep neural network in frequency domain","year":"2018","author":"xu","key":"ref18"},{"journal-title":"On the Spectral Bias of Neural Networks","year":"2018","author":"rahaman","key":"ref19"},{"journal-title":"On first-order meta-learning algorithms","year":"2018","author":"nichol","key":"ref28"},{"journal-title":"Distilling the knowledge in a neural network","year":"2015","author":"hinton","key":"ref4"},{"journal-title":"Auto-meta Automated gradient based meta learner search","year":"2018","author":"kim","key":"ref27"},{"key":"ref3","first-page":"21","article-title":"Ssd: Single shot multibox detector","author":"liu","year":"0","journal-title":"European Conference on Computer Vision"},{"journal-title":"Fitnets Hints for thin deep nets","year":"2014","author":"romero","key":"ref6"},{"journal-title":"Recasting gradient-based meta-learning as hierarchical bayes","year":"2018","author":"grant","key":"ref29"},{"key":"ref5","first-page":"2654","article-title":"Do deep nets really need to be deep?","author":"ba","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"950","article-title":"A simple weight decay can improve generalization","author":"krogh","year":"0","journal-title":"Advances in neural information processing systems 1992"},{"journal-title":"Actor-mimic Deep multitask and transfer reinforcement learning","year":"2015","author":"parisotto","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2708039"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"journal-title":"Opening the black box of deep neural networks via information","year":"2017","author":"shwartz-ziv","key":"ref20"},{"journal-title":"Under-standing deep learning requires rethinking generalization","year":"2016","author":"zhang","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab3985"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"journal-title":"Entropy-SGD Biasing Gradient Descent Into Wide Valleys","year":"2016","author":"chaudhari","key":"ref23"},{"journal-title":"Bayesian model-agnostic meta-learning","year":"2018","author":"kim","key":"ref26"},{"journal-title":"Meta-learning and universality Deep representations and gradient descent can approximate any learning algorithm","year":"2017","author":"finn","key":"ref25"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2021,1,10]]},"location":"Milan, Italy","end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412047.pdf?arnumber=9412047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:39Z","timestamp":1652197239000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412047\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412047","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}