Pyramidal Dilation Attention Convolutional Network With Active and Self-Paced Learning for Hyperspectral Image Classification
In recent years, deep neural networks have been widely used for hyperspectral image (HSI) classification and have shown excellent performance using numerous labeled samples. The acquisition of HSI labels is usually based on the field investigation, which is expensive and time consuming. Hence, the a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10018878/ |
| _version_ | 1797330406212632576 |
|---|---|
| author | Wenhui Hou Na Chen Jiangtao Peng Weiwei Sun Qian Du |
| author_facet | Wenhui Hou Na Chen Jiangtao Peng Weiwei Sun Qian Du |
| author_sort | Wenhui Hou |
| collection | DOAJ |
| description | In recent years, deep neural networks have been widely used for hyperspectral image (HSI) classification and have shown excellent performance using numerous labeled samples. The acquisition of HSI labels is usually based on the field investigation, which is expensive and time consuming. Hence, the available labels are usually limited, which affects the efficiency of deep HSI classification methods. To improve the classification performance while reducing the labeling cost, this article proposes a semisupervised deep learning (DL) method for HSI classification, named pyramidal dilation attention convolutional network with active and self-paced learning (PDAC-ASPL), which integrates active learning (AL), self-paced learning (SPL), and DL into a unified framework. First, a densely connected pyramidal dilation attention convolutional network is trained with a limited number of labeled samples. Then, the most informative samples from the unlabeled set are selected by AL and queried real labels, and the highest confidence samples with corresponding pseudo labels are extracted by SPL. Finally, the samples from AL and SPL are added to the training set to retrain the network. Compared with some DL- and AL-based HSI classification methods, our PDAC-ASPL achieves better performance on four HSI datasets. |
| first_indexed | 2024-03-08T07:19:23Z |
| format | Article |
| id | doaj.art-70090416c7424200ad2b770ee680c0bb |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-03-08T07:19:23Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-70090416c7424200ad2b770ee680c0bb2024-02-03T00:01:56ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352023-01-01161503151810.1109/JSTARS.2023.323756610018878Pyramidal Dilation Attention Convolutional Network With Active and Self-Paced Learning for Hyperspectral Image ClassificationWenhui Hou0Na Chen1Jiangtao Peng2https://orcid.org/0000-0002-4759-0584Weiwei Sun3https://orcid.org/0000-0003-3399-7858Qian Du4https://orcid.org/0000-0001-8354-7500Hubei Key Laboratory of Applied Mathematics, Faculty of Mathematics and Statistics, Hubei University, Wuhan, ChinaHubei Key Laboratory of Applied Mathematics, Faculty of Mathematics and Statistics, Hubei University, Wuhan, ChinaHubei Key Laboratory of Applied Mathematics, Faculty of Mathematics and Statistics, Hubei University, Wuhan, ChinaDepartment of Geography and Spatial Information Techniques, Ningbo University, Ningbo, ChinaDepartment of Electrical and Computer Engineering, Mississippi State University, Mississippi State, MS, USAIn recent years, deep neural networks have been widely used for hyperspectral image (HSI) classification and have shown excellent performance using numerous labeled samples. The acquisition of HSI labels is usually based on the field investigation, which is expensive and time consuming. Hence, the available labels are usually limited, which affects the efficiency of deep HSI classification methods. To improve the classification performance while reducing the labeling cost, this article proposes a semisupervised deep learning (DL) method for HSI classification, named pyramidal dilation attention convolutional network with active and self-paced learning (PDAC-ASPL), which integrates active learning (AL), self-paced learning (SPL), and DL into a unified framework. First, a densely connected pyramidal dilation attention convolutional network is trained with a limited number of labeled samples. Then, the most informative samples from the unlabeled set are selected by AL and queried real labels, and the highest confidence samples with corresponding pseudo labels are extracted by SPL. Finally, the samples from AL and SPL are added to the training set to retrain the network. Compared with some DL- and AL-based HSI classification methods, our PDAC-ASPL achieves better performance on four HSI datasets.https://ieeexplore.ieee.org/document/10018878/Active learning (AL)deep learning (DL)hyperspectral image (HSI) classificationself-paced learning (SPL) |
| spellingShingle | Wenhui Hou Na Chen Jiangtao Peng Weiwei Sun Qian Du Pyramidal Dilation Attention Convolutional Network With Active and Self-Paced Learning for Hyperspectral Image Classification IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Active learning (AL) deep learning (DL) hyperspectral image (HSI) classification self-paced learning (SPL) |
| title | Pyramidal Dilation Attention Convolutional Network With Active and Self-Paced Learning for Hyperspectral Image Classification |
| title_full | Pyramidal Dilation Attention Convolutional Network With Active and Self-Paced Learning for Hyperspectral Image Classification |
| title_fullStr | Pyramidal Dilation Attention Convolutional Network With Active and Self-Paced Learning for Hyperspectral Image Classification |
| title_full_unstemmed | Pyramidal Dilation Attention Convolutional Network With Active and Self-Paced Learning for Hyperspectral Image Classification |
| title_short | Pyramidal Dilation Attention Convolutional Network With Active and Self-Paced Learning for Hyperspectral Image Classification |
| title_sort | pyramidal dilation attention convolutional network with active and self paced learning for hyperspectral image classification |
| topic | Active learning (AL) deep learning (DL) hyperspectral image (HSI) classification self-paced learning (SPL) |
| url | https://ieeexplore.ieee.org/document/10018878/ |
| work_keys_str_mv | AT wenhuihou pyramidaldilationattentionconvolutionalnetworkwithactiveandselfpacedlearningforhyperspectralimageclassification AT nachen pyramidaldilationattentionconvolutionalnetworkwithactiveandselfpacedlearningforhyperspectralimageclassification AT jiangtaopeng pyramidaldilationattentionconvolutionalnetworkwithactiveandselfpacedlearningforhyperspectralimageclassification AT weiweisun pyramidaldilationattentionconvolutionalnetworkwithactiveandselfpacedlearningforhyperspectralimageclassification AT qiandu pyramidaldilationattentionconvolutionalnetworkwithactiveandselfpacedlearningforhyperspectralimageclassification |