Efficient Layer Compression Without Pruning
Author:
Affiliation:
1. College of Electrical and Information Engineering, Hunan University, Changsha, China
2. School of Astronautics, Beihang University, Beijing, China
3. School of Computer Science, University of Nottingham, Nottingham, U.K.
Funder
National Natural Science Fund of China
Science and Technology Plan Project Fund of Hunan Province
Key Research and Development Program of Hunan
Natural Science Fund of Hunan Province
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
Computer Graphics and Computer-Aided Design,Software
Link
http://xplorestaging.ieee.org/ielx7/83/9991910/10214522.pdf?arnumber=10214522
Reference66 articles.
1. ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting
2. Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration
3. Shallowing Deep Networks: Layer-Wise Pruning Based on Feature Representations
4. Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration
5. MobileNetV2: Inverted Residuals and Linear Bottlenecks
Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Taxi Passenger Flow Prediction Based on Hotspot Clustering and Neural Networks;2023 IEEE 3rd International Conference on Data Science and Computer Application (ICDSCA);2023-10-27
2. Dif-Fusion: Toward High Color Fidelity in Infrared and Visible Image Fusion With Diffusion Models;IEEE Transactions on Image Processing;2023
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3