Early Labeled and Small Loss Selection Semi-Supervised Learning Method for Remote Sensing Image Scene Classification
The classification of aerial scenes has been extensively studied as the basic work of remote sensing image processing and interpretation. However, the performance of remote sensing image scene classification based on deep neural networks is limited by the number of labeled samples. In order to allev...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/20/4039 |
| _version_ | 1797513242053967872 |
|---|---|
| author | Ye Tian Yuxin Dong Guisheng Yin |
| author_facet | Ye Tian Yuxin Dong Guisheng Yin |
| author_sort | Ye Tian |
| collection | DOAJ |
| description | The classification of aerial scenes has been extensively studied as the basic work of remote sensing image processing and interpretation. However, the performance of remote sensing image scene classification based on deep neural networks is limited by the number of labeled samples. In order to alleviate the demand for massive labeled samples, various methods have been proposed to apply semi-supervised learning to train the classifier using labeled and unlabeled samples. However, considering the complex contextual relationship and huge spatial differences, the existing semi-supervised learning methods bring different degrees of incorrectly labeled samples when pseudo-labeling unlabeled data. In particular, when the number of labeled samples is small, it affects the generalization performance of the model. In this article, we propose a novel semi-supervised learning method with early labeled and small loss selection. First, the model learns the characteristics of simple samples in the early stage and uses multiple early models to screen out a small number of unlabeled samples for pseudo-labeling based on this characteristic. Then, the model is trained in a semi-supervised manner by combining labeled samples, pseudo-labeled samples, and unlabeled samples. In the training process of the model, small loss selection is used to further eliminate some of the noisy labeled samples to improve the recognition accuracy of the model. Finally, in order to verify the effectiveness of the proposed method, it is compared with several state-of-the-art semi-supervised classification methods. The results show that when there are only a few labeled samples in remote sensing image scene classification, our method is always better than previous methods. |
| first_indexed | 2024-03-10T06:13:55Z |
| format | Article |
| id | doaj.art-0149a9d2cab84fe5bd703d0693745dad |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T06:13:55Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-0149a9d2cab84fe5bd703d0693745dad2023-11-22T19:53:13ZengMDPI AGRemote Sensing2072-42922021-10-011320403910.3390/rs13204039Early Labeled and Small Loss Selection Semi-Supervised Learning Method for Remote Sensing Image Scene ClassificationYe Tian0Yuxin Dong1Guisheng Yin2College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, ChinaCollege of Computer Science and Technology, Harbin Engineering University, Harbin 150001, ChinaCollege of Computer Science and Technology, Harbin Engineering University, Harbin 150001, ChinaThe classification of aerial scenes has been extensively studied as the basic work of remote sensing image processing and interpretation. However, the performance of remote sensing image scene classification based on deep neural networks is limited by the number of labeled samples. In order to alleviate the demand for massive labeled samples, various methods have been proposed to apply semi-supervised learning to train the classifier using labeled and unlabeled samples. However, considering the complex contextual relationship and huge spatial differences, the existing semi-supervised learning methods bring different degrees of incorrectly labeled samples when pseudo-labeling unlabeled data. In particular, when the number of labeled samples is small, it affects the generalization performance of the model. In this article, we propose a novel semi-supervised learning method with early labeled and small loss selection. First, the model learns the characteristics of simple samples in the early stage and uses multiple early models to screen out a small number of unlabeled samples for pseudo-labeling based on this characteristic. Then, the model is trained in a semi-supervised manner by combining labeled samples, pseudo-labeled samples, and unlabeled samples. In the training process of the model, small loss selection is used to further eliminate some of the noisy labeled samples to improve the recognition accuracy of the model. Finally, in order to verify the effectiveness of the proposed method, it is compared with several state-of-the-art semi-supervised classification methods. The results show that when there are only a few labeled samples in remote sensing image scene classification, our method is always better than previous methods.https://www.mdpi.com/2072-4292/13/20/4039remote sensing imagesscene classificationsemi-supervised classificationsmall loss selection |
| spellingShingle | Ye Tian Yuxin Dong Guisheng Yin Early Labeled and Small Loss Selection Semi-Supervised Learning Method for Remote Sensing Image Scene Classification Remote Sensing remote sensing images scene classification semi-supervised classification small loss selection |
| title | Early Labeled and Small Loss Selection Semi-Supervised Learning Method for Remote Sensing Image Scene Classification |
| title_full | Early Labeled and Small Loss Selection Semi-Supervised Learning Method for Remote Sensing Image Scene Classification |
| title_fullStr | Early Labeled and Small Loss Selection Semi-Supervised Learning Method for Remote Sensing Image Scene Classification |
| title_full_unstemmed | Early Labeled and Small Loss Selection Semi-Supervised Learning Method for Remote Sensing Image Scene Classification |
| title_short | Early Labeled and Small Loss Selection Semi-Supervised Learning Method for Remote Sensing Image Scene Classification |
| title_sort | early labeled and small loss selection semi supervised learning method for remote sensing image scene classification |
| topic | remote sensing images scene classification semi-supervised classification small loss selection |
| url | https://www.mdpi.com/2072-4292/13/20/4039 |
| work_keys_str_mv | AT yetian earlylabeledandsmalllossselectionsemisupervisedlearningmethodforremotesensingimagesceneclassification AT yuxindong earlylabeledandsmalllossselectionsemisupervisedlearningmethodforremotesensingimagesceneclassification AT guishengyin earlylabeledandsmalllossselectionsemisupervisedlearningmethodforremotesensingimagesceneclassification |