FewHshot image classification method based on sliding feature vectors

doi:10.13229/j.cnki.jdxbgxb20200532

	FewHshot image classification method based on sliding feature vectors
	Cao, Jie1,2 ; Qu, Xue 3; Li, Xiao-Xu 1
	2021-09-01
发表期刊	Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition)
ISSN	16715497
卷号	51 期号:5 页码:1785-1791
摘要	In the task of few-shot image classification, the extremely limited number of labeled examples per class can hardly represent the real class distribution effectively, which is the main reason for misclassification. To tackle this problem, we propose a method which named Sliding Feature Vectors Neural Network (SFV). The method aims to assemble all the local sliding feature vectors of samples from the same class to construct the class-level feature spaces, and then it utilized the image-to-class measure to classify the query samples. That means on the measure stage, SFV compare the similarity between the class and the query sample. SFV expands the class feature space by adding the edge information of feature blocks and correlation of their position and structures to maximize the utilization of the deep feature maps when the sample is extremely limited, which can ease overfitting problem caused by small sample data. Experimental study on benchmark datasets consistently shows its superiority over the related other framework, especially on fine-grained datasets, it achieves state-of-the-art. © 2021, Jilin University Press. All right reserved.
关键词	Query processing Vector spaces Class distributions Classification methods Computer applications technologies Feature space Features vector Few-shot learning Images classification Local feature Metric learning Misclassifications
DOI	10.13229/j.cnki.jdxbgxb20200532
收录类别	EI
语种	中文
出版者	Editorial Board of Jilin University
EI入藏号	20213910962768
EI主题词	Computer vision
EI分类号	723.5 Computer Applications ; 741.2 Vision ; 921 Mathematics
引用统计	无
文献类型	期刊论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/150886
专题	兰州理工大学
作者单位	1.School of Computer and Communication, Lanzhou University of Technology, Lanzhou; 730050, China; 2.Engineering Research Center of Urban Railway Transportation of Gansu Province, Lanzhou; 730050, China; 3.School of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou; 730050, China
第一作者单位	兰州理工大学
第一作者的第一单位	兰州理工大学
推荐引用方式 GB/T 7714	Cao, Jie,Qu, Xue,Li, Xiao-Xu. FewHshot image classification method based on sliding feature vectors[J]. Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition),2021,51(5):1785-1791.
APA	Cao, Jie,Qu, Xue,&Li, Xiao-Xu.(2021).FewHshot image classification method based on sliding feature vectors.Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition),51(5),1785-1791.
MLA	Cao, Jie,et al."FewHshot image classification method based on sliding feature vectors".Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition) 51.5(2021):1785-1791.