中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 智能制造技术与系统研究中心
  5. 多维数据分析团队
PSigmoid: Improving squeeze-and-excitation block with parametric sigmoid

文献类型：期刊论文

作者Ying, Yao2; Zhang, Nengbo4; Shan, Peng2; Miao, Ligang1; Sun, Peng3; Peng, Silong5
刊名APPLIED INTELLIGENCE
出版日期2021-03-09
页码13
ISSN号0924-669X
关键词Activation function Sigmoid Parametric sigmoid Squeeze-and-excitation Convolutional neural network
DOI10.1007/s10489-021-02247-z
通讯作者Shan, Peng(6094079@qq.com)
英文摘要Squeeze-and-Excitation (SE) Networks won the last ImageNet Large-Scale Visual Recognition Challenge (ILSVRC) classification competition and is very popular in today's vision community. The SE block is the core of Squeeze-and-Excitation Network (SENet), which adaptively recalibrates channel-wise features and suppresses less useful ones. Since SE blocks can be directly used in existing models and effectively improve performance, SE blocks are widely used in a variety of tasks. In this paper, we propose a novel Parametric Sigmoid (PSigmoid) to enhance the SE block. We named the new module PSigmoid SE (PSE) block. The PSE block can not only suppress features in a channel-wise manner, but also enhance features. We evaluate the performance of our method on four common datasets including CIFAR-10, CIFAR-100, SVHN and Tiny ImageNet. Experimental results show the effectiveness of our method. In addition, we compare the differences between the PSE block and the SE block through a detailed analysis of the configuration. Finally, we use a combination of PSE block and SE block to obtain better performance.
资助项目National Natural Science Foundation of China[61601104] ; Fundamental Research Funds for the Central Universities[N2023021]
WOS研究方向Computer Science
语种英语
出版者SPRINGER
WOS记录号WOS:000626811800001
资助机构National Natural Science Foundation of China ; Fundamental Research Funds for the Central Universities
源URL[http://ir.ia.ac.cn/handle/173211/44131]  
专题自动化研究所_智能制造技术与系统研究中心_多维数据分析团队
通讯作者Shan, Peng
作者单位1.Northeastern Univ, Sch Comp & Commun Engn, Shenyang 110819, Peoples R China
2.Northeastern Univ, Coll Informat Sci & Engn, Shenyang 110819, Peoples R China
3.Criminal Invest Police Univ China, Audio Visual & Image Technol Dept, Shenyang 110854, Peoples R China
4.Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen 518055, Peoples R China
5.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Ying, Yao,Zhang, Nengbo,Shan, Peng,et al. PSigmoid: Improving squeeze-and-excitation block with parametric sigmoid[J]. APPLIED INTELLIGENCE,2021:13.
APA Ying, Yao,Zhang, Nengbo,Shan, Peng,Miao, Ligang,Sun, Peng,&Peng, Silong.(2021).PSigmoid: Improving squeeze-and-excitation block with parametric sigmoid.APPLIED INTELLIGENCE,13.
MLA Ying, Yao,et al."PSigmoid: Improving squeeze-and-excitation block with parametric sigmoid".APPLIED INTELLIGENCE (2021):13.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。