Few-Shot Visual Classification Using Image Pairs With Binary Transformation

doi:10.1109/TCSVT.2019.2920783

	Few-Shot Visual Classification Using Image Pairs With Binary Transformation
	Zhang, Chunjie 3,4,5; Li, Chenghua 3; Cheng, Jian 1,2
刊名	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
	2020-09-01
卷号	30 期号:9 页码:2867-2871
关键词	Training Visualization Testing Correlation Image representation Automation Convolutional neural networks Few-shot classification visual classification image pair binary transformation object categorization
ISSN号	1051-8215
DOI	10.1109/TCSVT.2019.2920783
通讯作者	Zhang, Chunjie(ivazhangchunjie@gmail.com)
英文摘要	Accurately classifying images using few-shot samples have been widely explored by researchers. However, these methods have two drawbacks. First, images are often used independently. Second, class imbalance is ignored and hinders the classification accuracy with the increment of classes. To tackle these two drawbacks, in this paper, we propose a novel visual classification method using image pairs with binary transformation (IPBT). For one image, we bundle it with each training image into an image pair by concatenating the representations of the two images along with their similarity. The class consistency of two images is used to split the image pairs into binary groups. One group contains image pairs of the same class, while the other group consists of images pairs belonging to different classes. We train classifiers to separate the binary groups apart. To classify a testing image, we first bundle it with all the training images that are then predicted using the learned binary classifier. The image pair with the largest response is selected, and the testing image is assigned to the same class of the paired image. We conduct few-shot visual classification experiments on three public image datasets. The experimental results and analysis show the effectiveness of the proposed IPBT method.
资助项目	National Science Foundation of China (NSFC)[61872362] ; State Grid Corporation Science and Technology Project[5200-201916261A-0-0-00]
WOS关键词	LOW-RANK ; LABEL PROPAGATION ; FRAMEWORK
WOS研究方向	Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000567499300007
资助机构	National Science Foundation of China (NSFC) ; State Grid Corporation Science and Technology Project
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/41940]
专题	类脑芯片与系统研究
通讯作者	Zhang, Chunjie
作者单位	1.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing 100190, Peoples R China 4.Beijing Jiaotong Univ, Beijing Key Lab Adv Informat Sci & Network Techno, Beijing 100044, Peoples R China 5.Beijing Jiaotong Univ, Inst Informat Sci, Beijing 100044, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Chunjie,Li, Chenghua,Cheng, Jian. Few-Shot Visual Classification Using Image Pairs With Binary Transformation[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2020,30(9):2867-2871.
APA	Zhang, Chunjie,Li, Chenghua,&Cheng, Jian.(2020).Few-Shot Visual Classification Using Image Pairs With Binary Transformation.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,30(9),2867-2871.
MLA	Zhang, Chunjie,et al."Few-Shot Visual Classification Using Image Pairs With Binary Transformation".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 30.9(2020):2867-2871.