Knowledge Commons of Institute of Automation,CAS
Dynamical Channel Pruning by Conditional Accuracy Change for Deep Neural Networks | |
Chen, Zhiqiang1,2![]() ![]() ![]() ![]() ![]() | |
发表期刊 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
![]() |
ISSN | 1045-9227 |
2020-04 | |
卷号 | 无期号:无页码:无 |
通讯作者 | He, Huiguang(huiguang.he@ia.ac.cn) |
文章类型 | 长文 |
摘要 | Channel pruning is an effective technique that has been widely applied to deep neural network compression. However, many existing methods prune from a pretrained model, thus resulting in repetitious pruning and fine-tuning processes. In this article, we propose a dynamical channel pruning method, which prunes unimportant channels at the early stage of training. Rather than utilizing some indirect criteria (e.g., weight norm, absolute weight sum, and reconstruction error) to guide connection or channel pruning, we design criteria directly related to the final accuracy of a network to evaluate the importance of each channel. Specifically, a channelwise gate is designed to randomly enable or disable each channel so that the conditional accuracy changes (CACs) can be estimated under the condition of each channel disabled. Practically, we construct two effective and efficient criteria to dynamically estimate CAC at each iteration of training; thus, unimportant channels can be gradually pruned during the training process. Finally, extensive experiments on multiple data sets (i.e., ImageNet, CIFAR, and MNIST) with various networks (i.e., ResNet, VGG, and MLP) demonstrate that the proposed method effectively reduces the parameters and computations of baseline network while yielding the higher or competitive accuracy. Interestingly, if we Double the initial Channels and then Prune Half (DCPH) of them to baseline’s counterpart, it can enjoy a remarkable performance improvement by shaping a more desirable structure |
关键词 | Conditional accuracy change (CAC), direct criterion, dynamical channel pruning, neural network compression, structure shaping. |
学科门类 | 工学 ; 工学::计算机科学与技术(可授工学、理学学位) |
DOI | 10.1109/TNNLS.2020.2979517 |
URL | 查看原文 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[61976209] ; National Natural Science Foundation of China[61721004] ; CAS International Collaboration Key Project ; Strategic Priority Research Program of CAS[XDB32040200] |
项目资助者 | National Natural Science Foundation of China ; CAS International Collaboration Key Project ; Strategic Priority Research Program of CAS |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000616310400027 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
七大方向——子方向分类 | 类脑模型与计算 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/42215 |
专题 | 脑图谱与类脑智能实验室_神经计算与脑机交互 |
通讯作者 | He, Huiguang |
作者单位 | 1.Research Center for Brain-Inspired Intelligence, Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing 100190, China 2.University of Chinese Academy of Sciences (UCAS), Beijing 100049, China 3.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing 100190, China 4.Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Beijing 100190, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所; 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Chen, Zhiqiang,Xu, Ting-Bing,Du, Changde,et al. Dynamical Channel Pruning by Conditional Accuracy Change for Deep Neural Networks[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2020,无(无):无. |
APA | Chen, Zhiqiang,Xu, Ting-Bing,Du, Changde,Liu, Cheng-Lin,&He, Huiguang.(2020).Dynamical Channel Pruning by Conditional Accuracy Change for Deep Neural Networks.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,无(无),无. |
MLA | Chen, Zhiqiang,et al."Dynamical Channel Pruning by Conditional Accuracy Change for Deep Neural Networks".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 无.无(2020):无. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
定稿.pdf(4352KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论