{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T21:14:43Z","timestamp":1794950083513,"version":"4.9.1"},"reference-count":71,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.1109\/cvpr.2018.00907","type":"proceedings-article","created":{"date-parts":[[2018,12,17]],"date-time":"2018-12-17T20:49:37Z","timestamp":1545079777000},"page":"8697-8710","source":"Crossref","is-referenced-by-count":4412,"title":["Learning Transferable Architectures for Scalable Image Recognition"],"prefix":"10.1109","author":[{"given":"Barret","family":"Zoph","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vijay","family":"Vasudevan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathon","family":"Shlens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quoc V.","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref71","article-title":"Neural architecture search with reinforcement learning","author":"zoph","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref70","author":"zhang","year":"2017","journal-title":"ShuffleNet An Extremely Efficient Convolutional Neural Network for Mobile Devices"},{"key":"ref39","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref38","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref33","author":"larsson","year":"2016","journal-title":"Fractalnet Ultra-deep neural networks without residuals"},{"key":"ref32","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing System"},{"key":"ref31","author":"krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref30","article-title":"An empirical exploration of recurrent network architectures","author":"jozefowicz","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref35","author":"li","year":"2017","journal-title":"Learning to Optimize Neural Nets[J]"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref62","author":"wang","year":"2016","journal-title":"Learning to reinforcement learn"},{"key":"ref61","author":"ulyanov","year":"2016","journal-title":"Instance normalization The missing ingredient for fast stylization"},{"key":"ref63","article-title":"Planet-photo geolocation with convolutional neural networks","author":"weyand","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.351"},{"key":"ref64","author":"wichrowska","year":"2017","journal-title":"Learned optimizers that scale and generalize"},{"key":"ref27","article-title":"Deep networks with stochastic depth","author":"huang","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/1068009.1068315"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref29","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.154"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref2","author":"ba","year":"2016","journal-title":"Layer normalization"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.415"},{"key":"ref1","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref24","author":"howard","year":"2017","journal-title":"Mobilenets Efficient convolutional neural networks for mobile vision applications"},{"key":"ref23","first-page":"87","article-title":"Learning to learn using gradient descent","author":"hochreiter","year":"2001","journal-title":"Artificial Neural Networks"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref25","author":"hu","year":"2017","journal-title":"Squeeze-and-Excitation Networks"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref51","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref58","article-title":"Inception-v4, Inception-Resnet and the impact of residual connections on learning","author":"szegedy","year":"2016","journal-title":"International Conference on Learning Representations (ICLR) Workshop Track"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1162\/artl.2009.15.2.15202"},{"key":"ref56","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref55","article-title":"Scalable Bayesian optimization using deep neural networks","author":"snoek","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref54","article-title":"Practical Bayesian optimization of machine learning algorithms","author":"snoek","year":"2012","journal-title":"Neural Information Processing Systems"},{"key":"ref53","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref52","author":"shrivastava","year":"2016","journal-title":"Beyond skip connections Top-down modulation for object detection"},{"key":"ref10","article-title":"Fast and accurate deep network learning by exponential linear units (elus)","author":"clevert","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref40","first-page":"58","article-title":"Towards automatically-tuned neural networks","author":"mendoza","year":"2016","journal-title":"Proceedings of the 2016 workshop on Automatic Machine Learning"},{"key":"ref12","author":"devries","year":"2017","journal-title":"Improved regularization of convolutional neural networks with cutout"},{"key":"ref13","first-page":"647","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","volume":"32","author":"donahue","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref14","author":"duan","year":"2016","journal-title":"RL2 Fast reinforcement learning via slow reinforcement learning"},{"key":"ref15","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-007-0002-4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"ref18","article-title":"Shake-shake regularization of 3-branch residual networks","author":"gastaldi","year":"2017","journal-title":"International Conference on Learning Representations (ICLR) Workshop Track"},{"key":"ref19","article-title":"Hypernetworks","author":"ha","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref4","article-title":"Algorithms for hyper-parameter optimization","author":"bergstra","year":"2011","journal-title":"Neural Information Processing Systems"},{"key":"ref3","article-title":"Designing neural network architectures using reinforcement learning","author":"baker","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref6","article-title":"Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures","author":"bergstra","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref5","article-title":"Random search for hyperparameter optimization","author":"bergstra","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","author":"chen","year":"2017","journal-title":"Dual path networks"},{"key":"ref7","article-title":"Revisiting distributed synchronous sgd","author":"chen","year":"2016","journal-title":"International Conference on Learning Representations (ICLR) Workshop Track"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.4650"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref46","article-title":"Large-scale evolution of image classifiers","author":"real","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref45","article-title":"Optimization as a model for few-shot learning","author":"ravi","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref48","article-title":"Convolutional neural fabrics","author":"saxena","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref47","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref42","author":"miikkulainen","year":"2017","journal-title":"Evolving deep neural networks"},{"key":"ref41","author":"miconi","year":"2016","journal-title":"Neural networks with differentiable structure"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000579"},{"key":"ref43","author":"negrinho","year":"2017","journal-title":"Deeparchitect Automatically designing and training deep architectures"}],"event":{"name":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Salt Lake City, UT","start":{"date-parts":[[2018,6,18]]},"end":{"date-parts":[[2018,6,23]]}},"container-title":["2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8576498\/8578098\/08579005.pdf?arnumber=8579005","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T23:08:25Z","timestamp":1643238505000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8579005\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2018.00907","relation":{},"subject":[],"published":{"date-parts":[[2018,6]]}}}