Multiscale Graph Sample and Aggregate Network With Context-Aware Learning for Hyperspectral Image Classification
Recently, graph convolutional network (GCN) has achieved promising results in hyperspectral image (HSI) classification. However, GCN is a transductive learning method, which is difficult to aggregate the new node. Besides, the existing GCN-based methods divide graph construction and graph classifica...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9411656/ |
| _version_ | 1818890105932218368 |
|---|---|
| author | Yao Ding Xiaofeng Zhao Zhili Zhang Wei Cai Nengjun Yang |
| author_facet | Yao Ding Xiaofeng Zhao Zhili Zhang Wei Cai Nengjun Yang |
| author_sort | Yao Ding |
| collection | DOAJ |
| description | Recently, graph convolutional network (GCN) has achieved promising results in hyperspectral image (HSI) classification. However, GCN is a transductive learning method, which is difficult to aggregate the new node. Besides, the existing GCN-based methods divide graph construction and graph classification into two stages ignoring the influence of constructed graph error on classification results. Moreover, the available GCN-based methods fail to understand the global and contextual information of the graph. In this article, we propose a novel multiscale graph sample and aggregate network with a context-aware learning method for HSI classification. The proposed network adopts a multiscale graph sample and aggregate network (graphSAGE) to learn the multiscale features from the local regions graph, which improves the diversity of network input information and effectively solves the impact of original input graph errors on classification. By employing a context-aware mechanism to characterize the importance among spatially neighboring regions, deep contextual and global information of the graph can be learned automatically by focusing on important spatial targets. Meanwhile, the graph structure is reconstructed automatically based on the classified objects as network training, which is able to effectively reduce the influence of the initial graph error on the classification result. Extensive experiments are conducted on three real HSI datasets, which are demonstrated to outperform the compared state-of-the-art methods. |
| first_indexed | 2024-12-19T17:19:38Z |
| format | Article |
| id | doaj.art-18b56e49eccc451880e47934a73af68d |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-19T17:19:38Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-18b56e49eccc451880e47934a73af68d2022-12-21T20:12:42ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01144561457210.1109/JSTARS.2021.30744699411656Multiscale Graph Sample and Aggregate Network With Context-Aware Learning for Hyperspectral Image ClassificationYao Ding0https://orcid.org/0000-0003-2040-2640Xiaofeng Zhao1https://orcid.org/0000-0002-5459-5324Zhili Zhang2Wei Cai3Nengjun Yang4Xi'an Research Institute of High Technology, Xi'an, ChinaXi'an Research Institute of High Technology, Xi'an, ChinaXi'an Research Institute of High Technology, Xi'an, ChinaXi'an Research Institute of High Technology, Xi'an, ChinaXi'an Research Institute of High Technology, Xi'an, ChinaRecently, graph convolutional network (GCN) has achieved promising results in hyperspectral image (HSI) classification. However, GCN is a transductive learning method, which is difficult to aggregate the new node. Besides, the existing GCN-based methods divide graph construction and graph classification into two stages ignoring the influence of constructed graph error on classification results. Moreover, the available GCN-based methods fail to understand the global and contextual information of the graph. In this article, we propose a novel multiscale graph sample and aggregate network with a context-aware learning method for HSI classification. The proposed network adopts a multiscale graph sample and aggregate network (graphSAGE) to learn the multiscale features from the local regions graph, which improves the diversity of network input information and effectively solves the impact of original input graph errors on classification. By employing a context-aware mechanism to characterize the importance among spatially neighboring regions, deep contextual and global information of the graph can be learned automatically by focusing on important spatial targets. Meanwhile, the graph structure is reconstructed automatically based on the classified objects as network training, which is able to effectively reduce the influence of the initial graph error on the classification result. Extensive experiments are conducted on three real HSI datasets, which are demonstrated to outperform the compared state-of-the-art methods.https://ieeexplore.ieee.org/document/9411656/Deep contextualgraph convolutional network (GCN)hyperspectral image classificationmultiscale graph |
| spellingShingle | Yao Ding Xiaofeng Zhao Zhili Zhang Wei Cai Nengjun Yang Multiscale Graph Sample and Aggregate Network With Context-Aware Learning for Hyperspectral Image Classification IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Deep contextual graph convolutional network (GCN) hyperspectral image classification multiscale graph |
| title | Multiscale Graph Sample and Aggregate Network With Context-Aware Learning for Hyperspectral Image Classification |
| title_full | Multiscale Graph Sample and Aggregate Network With Context-Aware Learning for Hyperspectral Image Classification |
| title_fullStr | Multiscale Graph Sample and Aggregate Network With Context-Aware Learning for Hyperspectral Image Classification |
| title_full_unstemmed | Multiscale Graph Sample and Aggregate Network With Context-Aware Learning for Hyperspectral Image Classification |
| title_short | Multiscale Graph Sample and Aggregate Network With Context-Aware Learning for Hyperspectral Image Classification |
| title_sort | multiscale graph sample and aggregate network with context aware learning for hyperspectral image classification |
| topic | Deep contextual graph convolutional network (GCN) hyperspectral image classification multiscale graph |
| url | https://ieeexplore.ieee.org/document/9411656/ |
| work_keys_str_mv | AT yaoding multiscalegraphsampleandaggregatenetworkwithcontextawarelearningforhyperspectralimageclassification AT xiaofengzhao multiscalegraphsampleandaggregatenetworkwithcontextawarelearningforhyperspectralimageclassification AT zhilizhang multiscalegraphsampleandaggregatenetworkwithcontextawarelearningforhyperspectralimageclassification AT weicai multiscalegraphsampleandaggregatenetworkwithcontextawarelearningforhyperspectralimageclassification AT nengjunyang multiscalegraphsampleandaggregatenetworkwithcontextawarelearningforhyperspectralimageclassification |