what is new?分享 http://blog.sciencenet.cn/u/cogtech sparsity,manifolds,compressive sensing,dictionary learning,Data Reconstruction,Matrix Completion,Non-convex Optimization...


[转载]Deep Learning Model Compression for Image Analysis: Methods

已有 506 次阅读 2019-7-20 09:58 |系统分类:科研笔记|文章来源:转载

Deep Learning Model Compression for Image Analysis: Methods and Architectures



In my previous blog posts, I have reviewed well-known and recent deep learning algorithms for image classification and object detection. At Zyl, we aim to embed deep learning models directly within user’s smartphones to guarantee their privacy. This induces multiple constraints for these models known to be heavy and greedy in energy. Fortunately, at Zyl the embedded models are only used for inference1. Nevertheless, the computational cost is high even for inference and requires a lot of energy.

This blog post describes theoretical methods to reduce model size. Size reduction for deep learning models is an active field of research. Those methods are truly performant, but the specific type of machine learning models used involves extremely deep and complex architectures (Simonyan et al. (2014)He et al. (2015)Szegedy et al. (2016)). How can we simply transform a deep model into a lighter one without decreasing drastically its performances ? Moreover, does it exist specialized architectures to build light models while achieving state-of-the-art performances ? Note that researchers test their algorithms using different datasets. Thus the cited accuracies cannot be directly compared per se.


上一篇:[转载]Accelerating Convolutional Neural Networks on Raspberry Pi


该博文允许注册用户评论 请点击登录 评论 (0 个评论)


Archiver|手机版|科学网 ( 京ICP备14006957 )

GMT+8, 2019-10-18 14:21

Powered by ScienceNet.cn

Copyright © 2007- 中国科学报社