{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T18:42:53Z","timestamp":1725734573601},"reference-count":63,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"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":[[2019,10]]},"DOI":"10.1109\/iccv.2019.00196","type":"proceedings-article","created":{"date-parts":[[2020,2,28]],"date-time":"2020-02-28T10:27:52Z","timestamp":1582885672000},"page":"1872-1881","source":"Crossref","is-referenced-by-count":9,"title":["Adaptative Inference Cost With Convolutional Neural Mixture Models"],"prefix":"10.1109","author":[{"given":"Adria","family":"Ruiz","sequence":"first","affiliation":[]},{"given":"Jakob","family":"Verbeek","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"ICLRE","article-title":"Sgdr: Stochastic gradient descent with warm restarts","year":"2017","author":"loshchilov","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"journal-title":"NeurIPS","article-title":"Optimal brain damage","year":"1990","author":"lecun","key":"ref33"},{"journal-title":"ICLRE","article-title":"Fractalnet: Ultra-deep neural networks without residuals","year":"2017","author":"larsson","key":"ref32"},{"journal-title":"NeurIPS","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","year":"2017","author":"lakshminarayanan","key":"ref31"},{"journal-title":"NeurIPS","article-title":"Neural network ensembles, cross validation, and active learning","year":"1995","author":"krogh","key":"ref30"},{"journal-title":"ICLRE","article-title":"Darts: Differentiable architecture search","year":"2019","author":"liu","key":"ref37"},{"journal-title":"ICML","article-title":"Fixed point quantization of deep convolutional networks","year":"2016","author":"lin","key":"ref36"},{"journal-title":"ICLRE","article-title":"Pruning filters for efficient convnets","year":"2017","author":"li","key":"ref35"},{"journal-title":"arXiv preprint arXiv 1511 05271","article-title":"Why m heads are better than one: Training a diverse ensemble of deep networks","year":"2015","author":"lee","key":"ref34"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545535"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00506"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00190-X"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"journal-title":"NeurIPS","article-title":"Variational dropout and the local reparameterization trick","year":"2015","author":"kingma","key":"ref28"},{"journal-title":"ICLRE","article-title":"Auto-encoding variational Bayes","year":"2014","author":"kingma","key":"ref27"},{"journal-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref29"},{"journal-title":"NeurIPS","article-title":"Understanding dropout","year":"2013","author":"baldi","key":"ref2"},{"journal-title":"ECCV","article-title":"Maskconnect: Connectivity learning by gradient descent","year":"2018","author":"ahmed","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"journal-title":"ECCV","article-title":"Data-driven sparse structure selection for deep neural networks","year":"2018","author":"huang","key":"ref22"},{"journal-title":"ECCV","article-title":"Deep networks with stochastic depth","year":"2016","author":"huang","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_40"},{"journal-title":"arXiv preprint arXiv 1602 07360","article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and! 0.5 mb model size","year":"2016","author":"iandola","key":"ref23"},{"journal-title":"BMVC","article-title":"Speeding up convolutional neural networks with low rank expansions","year":"2014","author":"jaderberg","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"journal-title":"NeurIPS","article-title":"Swapout: Learning an ensemble of deep architectures","year":"2016","author":"singh","key":"ref50"},{"journal-title":"BMVC","article-title":"Data-free parameter pruning for deep neural networks","year":"2015","author":"srinivas","key":"ref51"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"journal-title":"ICLRE","article-title":"Slimmable neural networks","year":"2019","author":"yu","key":"ref57"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00368"},{"journal-title":"NeurIPS","article-title":"Residual networks behave like ensembles of relatively shallow networks","year":"2016","author":"veit","key":"ref55"},{"journal-title":"ICLRE","article-title":"Convolutional neural networks with low-rank regularization","year":"2016","author":"tai","key":"ref54"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"journal-title":"JMLR","article-title":"Dropout: a simple way to prevent neural networks from overfitting","year":"2014","author":"srivastava","key":"ref52"},{"journal-title":"NeurIPS","article-title":"Concrete dropout","year":"2017","author":"gal","key":"ref10"},{"journal-title":"ICML","article-title":"Structured variational learning of bayesian neural networks with horseshoe priors","year":"2018","author":"ghosh","key":"ref11"},{"journal-title":"ICML","article-title":"Multiplicative normalizing flows for variational bayesian neural networks","year":"2017","author":"louizos","key":"ref40"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.63"},{"journal-title":"ECCV","article-title":"Identity mappings in deep residual networks","year":"2016","author":"he","key":"ref13"},{"journal-title":"ECCV","article-title":"AMC: AutoML for model compression and acceleration on mobile devices","year":"2018","author":"he","key":"ref14"},{"journal-title":"Deep Learning and Representation Learning Workshop NIPS","article-title":"Distilling the knowledge in a neural network","year":"2015","author":"hinton","key":"ref15"},{"journal-title":"arXiv preprint arXiv 1704 04861","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"howard","key":"ref16"},{"journal-title":"ICLRE","article-title":"Multi-scale dense convolutional networks for efficient prediction","year":"2018","author":"huang","key":"ref17"},{"journal-title":"ICLRE","article-title":"Snapshot ensembles: Train 1, get m for free","year":"2017","author":"huang","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00291"},{"journal-title":"NeurIPS","article-title":"Learning efficient object detection models with knowledge distillation","year":"2017","author":"chen","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058655"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2018.8516453"},{"journal-title":"ICLRE","article-title":"Gradient descent provably optimizes over-parameterized neural networks","year":"2019","author":"du","key":"ref7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-21579-2_9"},{"journal-title":"ICLRE","article-title":"The lottery ticket hypothesis: Training pruned neural networks","year":"2018","author":"frankle","key":"ref9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1088\/0954-898X_8_3_004"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00941"},{"journal-title":"ICML","article-title":"Stochastic backpropagation and approximate inference in deep generative models","year":"2014","author":"rezende","key":"ref48"},{"journal-title":"NeurIPS","article-title":"Structured bayesian pruning via log-normal multiplicative noise","year":"2017","author":"neklyudov","key":"ref47"},{"journal-title":"ICLRE","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","year":"2017","author":"maddison","key":"ref42"},{"journal-title":"ICLRE","article-title":"Learning sparse neural networks through l 0 regularization","year":"2018","author":"louizos","key":"ref41"},{"journal-title":"ECCV","article-title":"Espnet: Efficient spatial pyramid of dilated convolutions for semantic segmentation","year":"2018","author":"mehta","key":"ref44"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.460"}],"event":{"name":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","start":{"date-parts":[[2019,10,27]]},"location":"Seoul, Korea (South)","end":{"date-parts":[[2019,11,2]]}},"container-title":["2019 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8972782\/9008105\/09010026.pdf?arnumber=9010026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:46:35Z","timestamp":1658094395000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9010026\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv.2019.00196","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}
