深度学习模型中间层特征压缩技术综述  

Review of intermediate deep feature compression

作　　者：汪维 徐龙 陈卓 Wang Wei;Xu Long;Chen Zhuo(State Key Laboratory of Space Weather,National Space Science Center,Chinese Academy of Sciences,Beijing 100190,China;University of Chinese Academy of Sciences,Beijing 100049,China;National Astronomical Observatories,Chinese Academy of Sciences,Beijing 100101,China;Institute of Infocomm Research,A*STAR,Singapore 999002,Singapore)

机构地区：[1]中国科学院国家空间科学中心空间天气国家重点实验室,北京100190 [2]中国科学院大学,北京100049 [3]中国科学院国家天文台,北京100101 [4]新加坡科技局通信研究院,新加坡999002

出　　处：《计算机应用研究》2023年第5期1281-1291,共11页Application Research of Computers

基　　金：国家重点研发计划资助项目(2021YFA1600504);国家自然科学基金资助项目(11790305)。

摘　　要：深度学习模型中间层特征压缩作为深度学习领域中一个新兴的研究热点被广泛关注并应用于边端—云端智能协同任务中。针对深度学习模型中间层特征压缩的研究现状,对当前压缩方式中存在的问题进行分析总结。首先,系统地分类阐述了基于图像/视频编解码框架、基于特征通道比特分配和基于深度学习网络结构的三种深度学习模型中间层特征压缩方式;随后,对比了三种深度学习模型中间层特征压缩方式在数据集上的表现;最后,探讨了当前深度学习模型中间层特征压缩研究面临的挑战,展望了中间层特征压缩技术未来的发展趋势。As a new research hotspot in deep learning,intermediate deep feature compression has gotten a great deal of attention and has been applied to edge-cloud intelligent collaboration.This paper summarized the current state of research on the intermediate deep feature compression and analyzed the problems in the current methods.Firstly,it introduced three kinds of intermediate deep feature compression from aspects of image/video coding framework,channel bit allocation and network units.Then it did the comparisons of the data set performance between the three intermediate deep feature compression.Finally,this paper discussed the existing challenges and solutions in intermediate deep feature compression and looked forward to the feature trends of intermediate deep feature compression.

关 键 词：深度学习 边云端智能协作 特征压缩 编码框架 比特分配 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]