视觉深度学习模型压缩加速综述  被引量:1

Review of model compression and acceleration for visual deep learning

在线阅读下载全文

作  者:丁贵广[1,2] 陈辉[2] 王澳 杨帆 熊翊哲[1,2,3] 梁伊雯 DING Guiguang;CHEN Hui;WANG Ao;YANG Fan;XIONG Yizhe;LIANG Yiwen(School of Software,Tsinghua University,Beijing 100084,China;Beijing National Research Center for Information Science and Technology,Tsinghua University,Beijing 100084,China;Zhuoxi Institute of Brain and Intelligence,Hangzhou 311121,China)

机构地区:[1]清华大学软件学院,北京100084 [2]清华大学北京信息科学与技术国家研究中心,北京100084 [3]涿溪脑与智能研究所,浙江杭州311121

出  处:《智能系统学报》2024年第5期1072-1081,共10页CAAI Transactions on Intelligent Systems

基  金:国家自然科学基金项目(61925107,62271281);浙江省自然科学基金项目(LDT23F01013F01).

摘  要:近年来,深度学习模型规模越来越大,在嵌入式设备等资源受限环境中,大规模视觉深度学习模型难以实现高效推理部署。模型压缩加速可以有效解决该挑战。尽管已经出现相关工作的综述,但相关工作集中在卷积神经网络的压缩加速,缺乏对视觉Transformer模型压缩加速方法的整理和对比分析。因此,本文以视觉深度学习模型压缩技术为核心,对卷积神经网络和视觉Transformer模型2个最重要的视觉深度模型进行了相关技术手段的整理,并对技术热点和挑战进行了总结和分析。本文旨在为研究者提供一个全面了解模型压缩和加速领域的视角,促进深度学习模型压缩加速技术的发展。Deep learning models have increasingly grown in scale in recent years.Large-scale visual deep learning models are difficult to efficiently infer and deploy in resource-constrained environments,such as embedded devices.Model compression and acceleration can effectively solve this challenge.Although reviews of related works are available,they generally focus on the compressing and acceleration of convolutional neural networks and lack the organization and comparative analysis of the compression and acceleration methods for visual Transformer models.This study focuses on visual deep learning model compression technology and summarizes and analyzes the relevant technical means for convolutional neural networks and visual Transformer models.Technical hotspots and challenges are also summarized and explored.This study provides researchers with a comprehensive understanding of model compression and acceleration fields,which promotes the development of compression and acceleration techniques for deep learning models.

关 键 词:视觉深度学习 模型压缩 轻量化结构 模型剪枝 模型量化 模型蒸馏 TRANSFORMER 序列剪枝 

分 类 号:TP18[自动化与计算机技术—控制理论与控制工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象