Ensemble synthetic oversampling with pixel pair for class-imbalanced and small-sized hyperspectral data classification
Hyperspectral images (HSI) suffer from limited labeled data and the curse of dimensionality, which makes it difficult to classify imbalanced and small-sized HSI data. To address the mentioned issues, pixel pair features is designed to handle small-size problem. However, the augmented data inherits t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-04-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843224000517 |
| _version_ | 1797224357358993408 |
|---|---|
| author | Wei Feng Yijun Long Gabriel Dauphin Yinghui Quan Wenjiang Huang Mengdao Xing |
| author_facet | Wei Feng Yijun Long Gabriel Dauphin Yinghui Quan Wenjiang Huang Mengdao Xing |
| author_sort | Wei Feng |
| collection | DOAJ |
| description | Hyperspectral images (HSI) suffer from limited labeled data and the curse of dimensionality, which makes it difficult to classify imbalanced and small-sized HSI data. To address the mentioned issues, pixel pair features is designed to handle small-size problem. However, the augmented data inherits the class imbalance and even exhibits a larger imbalance ratio. Therefore, the ensemble-based Synthetic Minority Oversampling Technique (SMOTE) is integrated into pixel pair features to deal with imbalanced datasets and strengthen the quality of the augmented datasets. The proposed method is evaluated on five groups of HSI datasets and compared against seven state-of-the-art contrast algorithms, including ensemble-CNN (E-CNN), CNN with pixel pair features, ensemble CNN with pixel pair features, spatial–spectral E-ResNet, E-Transfering-VGGNet, ContextualNet, and CNN with K-means SMOTE. The proposed method demonstrates superior performance across three distinct difficulty levels, as determined by its average performance rank on five HSI datasets. This underscores its effectiveness in mitigating small size and class imbalance challenges. |
| first_indexed | 2024-03-08T00:24:08Z |
| format | Article |
| id | doaj.art-b4a936dcdf1541ec8e8a140958ea9ea6 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-04-24T13:51:50Z |
| publishDate | 2024-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-b4a936dcdf1541ec8e8a140958ea9ea62024-04-04T05:03:32ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322024-04-01128103697Ensemble synthetic oversampling with pixel pair for class-imbalanced and small-sized hyperspectral data classificationWei Feng0Yijun Long1Gabriel Dauphin2Yinghui Quan3Wenjiang Huang4Mengdao Xing5Department of remote sensing science and technology, School of Electronic Engineering, Xidian University, Xi’an 710071, China; Xi’an Key Laboratory of Advanced Remote Sensing, Xi’an 710071, China; Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi’an 710071, China; Corresponding author at: Department of remote sensing science and technology, School of Electronic Engineering, Xidian University, Xi’an 710071, China.Department of remote sensing science and technology, School of Electronic Engineering, Xidian University, Xi’an 710071, China; Xi’an Key Laboratory of Advanced Remote Sensing, Xi’an 710071, China; Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi’an 710071, ChinaLaboratory of Information Processing and Transmission, L2TI, Institut Galilée, University Paris XIII, FranceDepartment of remote sensing science and technology, School of Electronic Engineering, Xidian University, Xi’an 710071, China; Xi’an Key Laboratory of Advanced Remote Sensing, Xi’an 710071, China; Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi’an 710071, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAcademy of Advanced Interdisciplinary Research, Xidian University, Xi’an 710071, ChinaHyperspectral images (HSI) suffer from limited labeled data and the curse of dimensionality, which makes it difficult to classify imbalanced and small-sized HSI data. To address the mentioned issues, pixel pair features is designed to handle small-size problem. However, the augmented data inherits the class imbalance and even exhibits a larger imbalance ratio. Therefore, the ensemble-based Synthetic Minority Oversampling Technique (SMOTE) is integrated into pixel pair features to deal with imbalanced datasets and strengthen the quality of the augmented datasets. The proposed method is evaluated on five groups of HSI datasets and compared against seven state-of-the-art contrast algorithms, including ensemble-CNN (E-CNN), CNN with pixel pair features, ensemble CNN with pixel pair features, spatial–spectral E-ResNet, E-Transfering-VGGNet, ContextualNet, and CNN with K-means SMOTE. The proposed method demonstrates superior performance across three distinct difficulty levels, as determined by its average performance rank on five HSI datasets. This underscores its effectiveness in mitigating small size and class imbalance challenges.http://www.sciencedirect.com/science/article/pii/S1569843224000517Hyperspectral image classificationImbalanced dataSmall-sized dataEnsemble learning |
| spellingShingle | Wei Feng Yijun Long Gabriel Dauphin Yinghui Quan Wenjiang Huang Mengdao Xing Ensemble synthetic oversampling with pixel pair for class-imbalanced and small-sized hyperspectral data classification International Journal of Applied Earth Observations and Geoinformation Hyperspectral image classification Imbalanced data Small-sized data Ensemble learning |
| title | Ensemble synthetic oversampling with pixel pair for class-imbalanced and small-sized hyperspectral data classification |
| title_full | Ensemble synthetic oversampling with pixel pair for class-imbalanced and small-sized hyperspectral data classification |
| title_fullStr | Ensemble synthetic oversampling with pixel pair for class-imbalanced and small-sized hyperspectral data classification |
| title_full_unstemmed | Ensemble synthetic oversampling with pixel pair for class-imbalanced and small-sized hyperspectral data classification |
| title_short | Ensemble synthetic oversampling with pixel pair for class-imbalanced and small-sized hyperspectral data classification |
| title_sort | ensemble synthetic oversampling with pixel pair for class imbalanced and small sized hyperspectral data classification |
| topic | Hyperspectral image classification Imbalanced data Small-sized data Ensemble learning |
| url | http://www.sciencedirect.com/science/article/pii/S1569843224000517 |
| work_keys_str_mv | AT weifeng ensemblesyntheticoversamplingwithpixelpairforclassimbalancedandsmallsizedhyperspectraldataclassification AT yijunlong ensemblesyntheticoversamplingwithpixelpairforclassimbalancedandsmallsizedhyperspectraldataclassification AT gabrieldauphin ensemblesyntheticoversamplingwithpixelpairforclassimbalancedandsmallsizedhyperspectraldataclassification AT yinghuiquan ensemblesyntheticoversamplingwithpixelpairforclassimbalancedandsmallsizedhyperspectraldataclassification AT wenjianghuang ensemblesyntheticoversamplingwithpixelpairforclassimbalancedandsmallsizedhyperspectraldataclassification AT mengdaoxing ensemblesyntheticoversamplingwithpixelpairforclassimbalancedandsmallsizedhyperspectraldataclassification |