An Impartial Semi-Supervised Learning Strategy for Imbalanced Classification on VHR Images

doi:10.3390/s20226699

CORC > 植物研究所 > 中国科学院植物研究所 > 植被与环境变化国家重点实验室

	An Impartial Semi-Supervised Learning Strategy for Imbalanced Classification on VHR Images
	Sun, Fei 2; Fang, Fang 1; Wang, Run 5; Wan, Bo 1; Guo, Qinghua 3; Li, Hong 1; Wu, Xincai 1
刊名	SENSORS
	2020
卷号	20 期号:22
关键词	image classification class imbalance impartial semi-supervised learning strategy (ISS) extreme gradient boosting (XGB) very-high-resolution (VHR)
DOI	10.3390/s20226699
文献子类	Article
英文摘要	Imbalanced learning is a common problem in remote sensing imagery-based land-use and land-cover classifications. Imbalanced learning can lead to a reduction in classification accuracy and even the omission of the minority class. In this paper, an impartial semi-supervised learning strategy based on extreme gradient boosting (ISS-XGB) is proposed to classify very high resolution (VHR) images with imbalanced data. ISS-XGB solves multi-class classification by using several semi-supervised classifiers. It first employs multi-group unlabeled data to eliminate the imbalance of training samples and then utilizes gradient boosting-based regression to simulate the target classes with positive and unlabeled samples. In this study, experiments were conducted on eight study areas with different imbalanced situations. The results showed that ISS-XGB provided a comparable but more stable performance than most commonly used classification approaches (i.e., random forest (RF), XGB, multilayer perceptron (MLP), and support vector machine (SVM)), positive and unlabeled learning (PU-Learning) methods (PU-BP and PU-SVM), and typical synthetic sample-based imbalanced learning methods. Especially under extremely imbalanced situations, ISS-XGB can provide high accuracy for the minority class without losing overall performance (the average overall accuracy achieves 85.92%). The proposed strategy has great potential in solving the imbalanced classification problems in remote sensing.
学科主题	Chemistry, Analytical ; Engineering, Electrical & Electronic ; Instruments & Instrumentation
电子版国际标准刊号	1424-8220
出版地	BASEL
WOS关键词	RANDOM FOREST ; MACHINE ; SMOTE ; PERFORMANCE ; CHALLENGES ; DIVERSITY ; ALGORITHM
WOS研究方向	Chemistry ; Engineering ; Instruments & Instrumentation
语种	英语
出版者	MDPI
WOS记录号	WOS:000594558300001
资助机构	Opening Fund of Key Laboratory of Geological Survey and Evaluation of Ministry of Education [GLAB2019ZR14] ; Fundamental Research Funds for the Central UniversitiesFundamental Research Funds for the Central Universities [26420190051]
内容类型	期刊论文
源URL	[http://ir.ibcas.ac.cn/handle/2S10CLM1/21507]
专题	植被与环境变化国家重点实验室
作者单位	1.Huanggang Normal Univ, Acad Comp, 146 Xinggang 2nd Rd, Huanggang 438000, Peoples R China 2.China Univ Geosci, Sch Geog & Informat Engn, Wuhan 430078, Peoples R China 3.China Univ Geosci, OfMinistry Educ, Key Lab Geol Survey & Evaluat, Wuhan 430078, Peoples R China 4.Chinese Acad Sci, State Key Lab Vegetat & Environm Change, Inst Bot, Beijing 100093, Peoples R China 5.China Univ Geosci, Natl Engn Res Ctr Geog Informat Syst, Wuhan 430078, Peoples R China
推荐引用方式 GB/T 7714	Sun, Fei,Fang, Fang,Wang, Run,et al. An Impartial Semi-Supervised Learning Strategy for Imbalanced Classification on VHR Images[J]. SENSORS,2020,20(22).
APA	Sun, Fei.,Fang, Fang.,Wang, Run.,Wan, Bo.,Guo, Qinghua.,...&Wu, Xincai.(2020).An Impartial Semi-Supervised Learning Strategy for Imbalanced Classification on VHR Images.SENSORS,20(22).
MLA	Sun, Fei,et al."An Impartial Semi-Supervised Learning Strategy for Imbalanced Classification on VHR Images".SENSORS 20.22(2020).