摘要:基于信息流分析的cnn逆向约简

Yu-Hsun Lin, Chun-Nan Chou, Edward Y. Chang
{"title":"摘要:基于信息流分析的cnn逆向约简","authors":"Yu-Hsun Lin, Chun-Nan Chou, Edward Y. Chang","doi":"10.1109/AIVR.2018.00014","DOIUrl":null,"url":null,"abstract":"This paper proposes BRIEF, a backward reduction algorithm that explores compact CNN-model designs from the information flow perspective. This algorithm can remove substantial non-zero weighting parameters (redundant neural channels) of a network by considering its dynamic behavior, which traditional model-compaction techniques cannot achieve. With the aid of our proposed algorithm, we achieve significant model reduction on ResNet-34 in the ImageNet scale (32.3% reduction), which is 3X better than the previous result (10.8%). Even for highly optimized models such as SqueezeNet and MobileNet, we can achieve additional 10.81% and 37.56% reduction, respectively, with negligible performance degradation.","PeriodicalId":371868,"journal":{"name":"2018 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"BRIEF: Backward Reduction of CNNs with Information Flow Analysis\",\"authors\":\"Yu-Hsun Lin, Chun-Nan Chou, Edward Y. Chang\",\"doi\":\"10.1109/AIVR.2018.00014\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper proposes BRIEF, a backward reduction algorithm that explores compact CNN-model designs from the information flow perspective. This algorithm can remove substantial non-zero weighting parameters (redundant neural channels) of a network by considering its dynamic behavior, which traditional model-compaction techniques cannot achieve. With the aid of our proposed algorithm, we achieve significant model reduction on ResNet-34 in the ImageNet scale (32.3% reduction), which is 3X better than the previous result (10.8%). Even for highly optimized models such as SqueezeNet and MobileNet, we can achieve additional 10.81% and 37.56% reduction, respectively, with negligible performance degradation.\",\"PeriodicalId\":371868,\"journal\":{\"name\":\"2018 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)\",\"volume\":\"5 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-07-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/AIVR.2018.00014\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AIVR.2018.00014","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

本文提出了一种反向约简算法BRIEF,该算法从信息流的角度探索了紧凑的cnn模型设计。该算法通过考虑网络的动态行为,可以去除网络中大量的非零权重参数(冗余神经通道),这是传统模型压缩技术无法实现的。在我们提出的算法的帮助下,我们在ResNet-34的ImageNet尺度上实现了显著的模型缩减(减少32.3%),比之前的结果(10.8%)好3倍。即使对于高度优化的模型,如SqueezeNet和MobileNet,我们也可以分别实现10.81%和37.56%的额外降低,而性能下降可以忽略不计。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
BRIEF: Backward Reduction of CNNs with Information Flow Analysis
This paper proposes BRIEF, a backward reduction algorithm that explores compact CNN-model designs from the information flow perspective. This algorithm can remove substantial non-zero weighting parameters (redundant neural channels) of a network by considering its dynamic behavior, which traditional model-compaction techniques cannot achieve. With the aid of our proposed algorithm, we achieve significant model reduction on ResNet-34 in the ImageNet scale (32.3% reduction), which is 3X better than the previous result (10.8%). Even for highly optimized models such as SqueezeNet and MobileNet, we can achieve additional 10.81% and 37.56% reduction, respectively, with negligible performance degradation.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
A Perceptual Evaluation of Generative Adversarial Network Real-Time Synthesized Drum Sounds in a Virtual Environment Virtual Crime Scene Understanding Head-Mounted Display FOV in Maritime Search and Rescue Object Detection [Publisher's information] A Combination of Feedback Control and Vision-Based Deep Learning Mechanism for Guiding Self-Driving Cars
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1