Improved Active Deep Learning for Semi-Supervised Classification of Hyperspectral Image
Hyperspectral image (HSI) data classification often faces the problem of the scarcity of labeled samples, which is considered to be one of the major challenges in the field of remote sensing. Although active deep networks have been successfully applied in semi-supervised classification tasks to addr...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/1/171 |
| _version_ | 1827667689421668352 |
|---|---|
| author | Qingyan Wang Meng Chen Junping Zhang Shouqiang Kang Yujing Wang |
| author_facet | Qingyan Wang Meng Chen Junping Zhang Shouqiang Kang Yujing Wang |
| author_sort | Qingyan Wang |
| collection | DOAJ |
| description | Hyperspectral image (HSI) data classification often faces the problem of the scarcity of labeled samples, which is considered to be one of the major challenges in the field of remote sensing. Although active deep networks have been successfully applied in semi-supervised classification tasks to address this problem, their performance inevitably meets the bottleneck due to the limitation of labeling cost. To address the aforementioned issue, this paper proposes a semi-supervised classification method for hyperspectral images that improves active deep learning. Specifically, the proposed model introduces the random multi-graph algorithm and replaces the expert mark in active learning with the anchor graph algorithm, which can label a considerable amount of unlabeled data precisely and automatically. In this way, a large number of pseudo-labeling samples would be added to the training subsets such that the model could be fine-tuned and the generalization performance could be improved without extra efforts for data manual labeling. Experiments based on three standard HSIs demonstrate that the proposed model can get better performance than other conventional methods, and they also outperform other studied algorithms in the case of a small training set. |
| first_indexed | 2024-03-10T03:22:46Z |
| format | Article |
| id | doaj.art-18f3dc515ec2429aaf7b3aa8820f11b1 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:22:46Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-18f3dc515ec2429aaf7b3aa8820f11b12023-11-23T12:14:16ZengMDPI AGRemote Sensing2072-42922021-12-0114117110.3390/rs14010171Improved Active Deep Learning for Semi-Supervised Classification of Hyperspectral ImageQingyan Wang0Meng Chen1Junping Zhang2Shouqiang Kang3Yujing Wang4School of Measurement-Control and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Measurement-Control and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, ChinaSchool of Measurement-Control and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Measurement-Control and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaHyperspectral image (HSI) data classification often faces the problem of the scarcity of labeled samples, which is considered to be one of the major challenges in the field of remote sensing. Although active deep networks have been successfully applied in semi-supervised classification tasks to address this problem, their performance inevitably meets the bottleneck due to the limitation of labeling cost. To address the aforementioned issue, this paper proposes a semi-supervised classification method for hyperspectral images that improves active deep learning. Specifically, the proposed model introduces the random multi-graph algorithm and replaces the expert mark in active learning with the anchor graph algorithm, which can label a considerable amount of unlabeled data precisely and automatically. In this way, a large number of pseudo-labeling samples would be added to the training subsets such that the model could be fine-tuned and the generalization performance could be improved without extra efforts for data manual labeling. Experiments based on three standard HSIs demonstrate that the proposed model can get better performance than other conventional methods, and they also outperform other studied algorithms in the case of a small training set.https://www.mdpi.com/2072-4292/14/1/171active deep learninghyperspectral imagesrandom multi-graphsmall samples |
| spellingShingle | Qingyan Wang Meng Chen Junping Zhang Shouqiang Kang Yujing Wang Improved Active Deep Learning for Semi-Supervised Classification of Hyperspectral Image Remote Sensing active deep learning hyperspectral images random multi-graph small samples |
| title | Improved Active Deep Learning for Semi-Supervised Classification of Hyperspectral Image |
| title_full | Improved Active Deep Learning for Semi-Supervised Classification of Hyperspectral Image |
| title_fullStr | Improved Active Deep Learning for Semi-Supervised Classification of Hyperspectral Image |
| title_full_unstemmed | Improved Active Deep Learning for Semi-Supervised Classification of Hyperspectral Image |
| title_short | Improved Active Deep Learning for Semi-Supervised Classification of Hyperspectral Image |
| title_sort | improved active deep learning for semi supervised classification of hyperspectral image |
| topic | active deep learning hyperspectral images random multi-graph small samples |
| url | https://www.mdpi.com/2072-4292/14/1/171 |
| work_keys_str_mv | AT qingyanwang improvedactivedeeplearningforsemisupervisedclassificationofhyperspectralimage AT mengchen improvedactivedeeplearningforsemisupervisedclassificationofhyperspectralimage AT junpingzhang improvedactivedeeplearningforsemisupervisedclassificationofhyperspectralimage AT shouqiangkang improvedactivedeeplearningforsemisupervisedclassificationofhyperspectralimage AT yujingwang improvedactivedeeplearningforsemisupervisedclassificationofhyperspectralimage |