CatBoost for RS Image Classification With Pseudo Label Support From Neighbor Patches-Based Clustering

被引：33
作者：
Samat, Alim [1 ,2 ,3 ]
Li, Erzhu [4 ]
Du, Peijun [5 ]
Liu, Sicong [6 ]
Miao, Zelang [7 ]
Zhang, Wei [5 ]
机构：
[1] Chinese Acad Sci, Xinjiang Inst Ecol & Geog, State Key Lab Desert & Oasis Ecol, Urumqi 830011, Peoples R China
[2] Chinese Acad Sci, Res Ctr Ecol & Environm Cent Asia, Urumqi 830011, Peoples R China
[3] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
[4] Jiangsu Normal Univ, Sch Geog Geomat & Planning, Xuzhou 221116, Jiangsu, Peoples R China
[5] Nanjing Univ, Sch Geog & Ocean Sci, Nanjing 210023, Peoples R China
[6] Tongji Univ, Coll Surveying & Geoinformat, Shanghai 200092, Peoples R China
[7] Cent South Univ, Sch Geosci & Info Phys, Changsha 410083, Peoples R China
来源：
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2022年 / 19卷
关键词：
Feature extraction; Boosting; Training; Error analysis; Clustering algorithms; Image color analysis; Task analysis; CatBoost; clustering; gradient boosting; image classification; neighbor patches; pseudo label features (PLFs); CONVOLUTIONAL NEURAL-NETWORK;
D O I：
10.1109/LGRS.2020.3038771
中图分类号：
P3 [地球物理学]; P59 [地球化学];
学科分类号：
0708 ; 070902 ;
摘要：
In this letter, CatBoost was first introduced and investigated for remote sensing (RS) image classification using diverse features. To improve the classification performance by fostering the effective and efficient spatial feature extraction, a new pseudo label features (PLFs) extraction method was proposed via multisize neighboring patches-based multiclustering. Experimental results on two hyperspectral and one PolSAR benchmarks showed that: 1) CatBoost is an advanced ensemble learning (EL) algorithm for classification of RS images using diverse features; 2) CatBoost has better capability of reducing the overfitting issue at large number of boosting iteration; and 3) proposed PLFs can result in compatible and even better classification results than using morphological profiles (MPs) and MPs with partial reconstruction (MPPR) spatial features.
引用
收藏
页数：5
相关论文
共 34 条
[1]  
[Anonymous], 2021, IEEE Trans. Broadcast.
[2]   Classification of hyperspectral data from urban areas based on extended morphological profiles [J].
Benediktsson, JA ;
Palmason, JA ;
Sveinsson, JR .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2005, 43 (03) :480-491
[3]   Pseudo Label Based on Multiple Clustering for Unsupervised Cross-Domain Person Re-Identification [J].
Chen, Shuni ;
Fan, Zheyi ;
Yin, Jianyuan .
IEEE SIGNAL PROCESSING LETTERS, 2020, 27 :1460-1464
[4]   XGBoost: A Scalable Tree Boosting System [J].
Chen, Tianqi ;
Guestrin, Carlos .
KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :785-794
[5]   A Sparse Representation-Based Sample Pseudo-Labeling Method for Hyperspectral Image Classification [J].
Cui, Binge ;
Cui, Jiandi ;
Lu, Yan ;
Guo, Nannan ;
Gong, Maoguo .
REMOTE SENSING, 2020, 12 (04)
[6]  
Daoud EA, 2019, INT J COMPUT INF ENG, V13, P6
[7]   Gaofen-3 PolSAR Image Classification via XGBoost and Polarimetric Spatial Information [J].
Dong, Hao ;
Xu, Xin ;
Wang, Lei ;
Pu, Fangling .
SENSORS, 2018, 18 (02)
[8]  
Dorogush Anna Veronika, 2018, P WORKSHOP ML SYSTEM
[9]   Random Forest and Rotation Forest for fully polarized SAR image classification using polarimetric and spatial features [J].
Du, Peijun ;
Samat, Alim ;
Waske, Bjoern ;
Liu, Sicong ;
Li, Zhenhong .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2015, 105 :38-53
[10]   Collaborative learning of lightweight convolutional neural network and deep clustering for hyperspectral image semi-supervised classification with limited training samples [J].
Fang, Bei ;
Li, Ying ;
Zhang, Haokui ;
Chan, Jonathan Cheung-Wai .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2020, 161 :164-178
1234