文献类型：期刊文献

英文题名：Union-net: lightweight deep neural network model suitable for small data sets

作者：Zhou, Jingyi[1];He, Qingfang[2];Cheng, Guang[2];Lin, Zhiying[2]

第一作者：Zhou, Jingyi

通讯作者：He, QF[1];Lin, ZY[1]

机构：[1]Inst Sci & Tech Res Arch, Beijing 100050, Peoples R China;[2]Beijing Union Univ, Inst Comp Technol, Beijing 100101, Peoples R China

第一机构：Inst Sci & Tech Res Arch, Beijing 100050, Peoples R China

通讯机构：[1]corresponding author), Beijing Union Univ, Inst Comp Technol, Beijing 100101, Peoples R China.|[1141734]北京联合大学智慧城市学院;[11417]北京联合大学;

年份：0

外文期刊名：JOURNAL OF SUPERCOMPUTING

收录：;EI(收录号：20224813171885);Scopus(收录号：2-s2.0-85142531643);WOS:【SCI-EXPANDED(收录号:WOS:000888685800001)】；

基金：This work was supported by Beijing Natural Science Foundation (No.L191006) and Academic Research Projects of Beijing Union University (No.XP202021).

语种：英文

外文关键词：Small data sets; Deep learning; Pre-trained model; Shallow network; CNN model

摘要：Traditional deep learning models prefer large data sets, and in reality small data sets are easier to obtain. It is more practical to build models suitable for small data sets. Based on CNN, this paper proposes the concept of union convolution to build a deep learning model Union-net that is suitable for small data sets. The Union-net has small model size and superior performance. In this paper, the model is tested based on multiple commonly used data sets. The experimental results show that Union-net outperforms most models when dealing with small datasets, and Union-net outperforms other models when dealing with complex classification tasks or dealing with few-shot datasets. The codes for this paper have been uploaded to https://github. com/yeaso/union-net.