Bayesian Filter Pruning for Deep Convolutional Neural Network Compression

Haomin Lin, Tianyou Yu
{"title":"Bayesian Filter Pruning for Deep Convolutional Neural Network Compression","authors":"Haomin Lin, Tianyou Yu","doi":"10.1109/ICCECE58074.2023.10135208","DOIUrl":null,"url":null,"abstract":"Network pruning has been demonstrated as a feasible approach in reducing model complexity and accelerating the process of inference, which make it possible to deploy deep neural network in resource-limited devices. Many previous works on network pruning consider the magnitude of parameters or other intrinsic properties in point-estimates based network as the criterion of module selection, which are incapable of estimating uncertainty of parameters. In this paper, we propose a novel Bayesian filter pruning method, which leverages the advantage of Bayesian Deep Learning (BDL), by exploring the properties of distribution in weight. The proposed method removes redundant filters from a Bayesian network by a criterion of the proposed Signal to Noise Ratio (SNR) that combines properties of importance with uncertainty of filters. Experimental results on two benchmark datasets show the efficiency of our method in maintaining balance between compression and acceleration.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCECE58074.2023.10135208","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Network pruning has been demonstrated as a feasible approach in reducing model complexity and accelerating the process of inference, which make it possible to deploy deep neural network in resource-limited devices. Many previous works on network pruning consider the magnitude of parameters or other intrinsic properties in point-estimates based network as the criterion of module selection, which are incapable of estimating uncertainty of parameters. In this paper, we propose a novel Bayesian filter pruning method, which leverages the advantage of Bayesian Deep Learning (BDL), by exploring the properties of distribution in weight. The proposed method removes redundant filters from a Bayesian network by a criterion of the proposed Signal to Noise Ratio (SNR) that combines properties of importance with uncertainty of filters. Experimental results on two benchmark datasets show the efficiency of our method in maintaining balance between compression and acceleration.
深度卷积神经网络压缩的贝叶斯滤波剪枝
网络修剪作为一种降低模型复杂度和加速推理过程的可行方法,为在资源有限的设备中部署深度神经网络提供了可能。以往的许多网络剪枝研究都将基于点估计的网络中参数的大小或其他固有性质作为模块选择的准则,无法估计参数的不确定性。在本文中,我们提出了一种新的贝叶斯滤波剪枝方法,该方法利用贝叶斯深度学习(BDL)的优势,通过探索权重分布的性质。该方法通过将滤波器的重要性和不确定性结合起来的信噪比(SNR)标准,从贝叶斯网络中去除冗余滤波器。在两个基准数据集上的实验结果表明,该方法能够有效地保持压缩和加速之间的平衡。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信