Active Learning for Hyperspectral Image Classification Using Kernel Sparse Representation Classifiers

被引：3

作者：

Bortiew, Amos ^{[1
]}

Patra, Swarnajyoti ^{[1
]}

Bruzzone, Lorenzo ^{[2
]}

机构：

[1] Tezpur Univ, Dept Comp Sci & Engn, Tezpur 784028, Assam, India

[2] Univ Trento, Dept Informat Engn & Comp Sci, I-38123 Trento, Italy

来源：

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2023年 / 20卷

关键词：

Uncertainty; Kernel; Dictionaries; Diversity reception; Redundancy; Training; Correlation; Active learning (AL); hyperpsectral image; kernel space; query function; sparse representation;

D O I：

10.1109/LGRS.2023.3264283

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：

Active learning (AL) is one of the popular approaches that can mitigate some of the drawbacks of supervised classification. Although sparse representation classifier (SRC) has already proven to be a robust classifier and successfully used in many applications, it is seldom used jointly with AL. In this letter, we propose a novel AL technique for SRCs. In the proposed model, the query function is designed by combining uncertainty and diversity criteria, both of which are defined by using the SRC in kernel space. The proposed technique outperforms other state-of-the-art methods in terms of classification performance.

引用

页数：5

共 20 条

[1]

[Anonymous], 2003, P 20 INT C MACH LEAR

[2] Hyperspectral Image Classification With Convolutional Neural Network and Active Learning [J].

Cao, Xiangyong ;

Yao, Jing ;

Xu, Zongben ;

Meng, Deyu .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2020, 58 (07) :4604-4616

[3] Hyperspectral Image Classification via Kernel Sparse Representation [J].

Chen, Yi ;

Nasrabadi, Nasser M. ;

Tran, Trac D. .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2013, 51 (01) :217-231

[4] Batch-Mode Active-Learning Methods for the Interactive Classification of Remote Sensing Images [J].

Demir, Begum ;

Persello, Claudio ;

Bruzzone, Lorenzo .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2011, 49 (03) :1014-1031

[5]

Huo L. -Z., 2016, PROC 8 WORKSHOP HYPE, P1

[6] Adaptive kernel sparse representation based on multiple feature learning for hyperspectral image classification [J].

Li, Dan ;

Wang, Qiang ;

Kong, Fanqiang .

NEUROCOMPUTING, 2020, 400 :97-112

[7] Segmentation of multispectral remote sensing images using active support vector machines [J].

Mitra, P ;

Shankar, BU ;

Pal, SK .

PATTERN RECOGNITION LETTERS, 2004, 25 (09) :1067-1074

[8] Hyperspectral Image Classification Based on Active Learning and Spectral-Spatial Feature Fusion Using Spatial Coordinates [J].

Mu, Caihong ;

Liu, Jian ;

Liu, Yi ;

Liu, Yijin .

IEEE ACCESS, 2020, 8 :6768-6781

[9] SVM Active Learning Approach for Image Classification Using Spatial Information [J].

Pasolli, Edoardo ;

Melgani, Farid ;

Tuia, Devis ;

Pacifici, Fabio ;

Emery, William J. .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2014, 52 (04) :2217-2233

[10] A Spectral-Spatial Multicriteria Active Learning Technique for Hyperspectral Image Classification [J].

Patra, Swarnajyoti ;

Bhardwaj, Kaushal ;

Bruzzone, Lorenzo .

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2017, 10 (12) :5213-5227

← 1 2 →