Semisupervised Dual-Dictionary Learning for Heterogeneous Transfer Learning on Cross-Scene Hyperspectral Images
Lack of labeled training samples is a big challenge for hyperspectral image (HSI) classification. In recent years, cross-scene classification has become a new research topic. In cross-scene classification, two closely related HSI scenes are considered, one contains adequate labeled samples, namely s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9110759/ |
| _version_ | 1818668719590604800 |
|---|---|
| author | Hong Chen Minchao Ye Ling Lei Huijuan Lu Yuntao Qian |
| author_facet | Hong Chen Minchao Ye Ling Lei Huijuan Lu Yuntao Qian |
| author_sort | Hong Chen |
| collection | DOAJ |
| description | Lack of labeled training samples is a big challenge for hyperspectral image (HSI) classification. In recent years, cross-scene classification has become a new research topic. In cross-scene classification, two closely related HSI scenes are considered, one contains adequate labeled samples, namely source scene, while the other one contains only a few labeled samples, namely target scene. The goal of cross-scene classification is utilizing the labeled samples in source scene to benefit the classification in target scene. In most cases, different HSIs are imaged by different sensors, leading to different feature dimensions (numbers of bands) in different scenes. In this situation, heterogeneous transfer learning is demanded. In this article, we propose a heterogeneous transfer learning algorithm namely semisupervised dual-dictionary nonnegative matrix factorization (SS-DDNMF). SS-DDNMF consists of two contributions. 1) Dual-dictionary nonnegative matrix factorization (DDNMF): DDNMF trains two dictionaries for source and target scenes, respectively, aiming at projecting the source and target features to a shared low-dimensional subspace, eliminating the difference between feature spaces. In DDNMF, within-scene and cross-scene graphs are built to maintain the similarities between pixels. 2) Semisupervised learning for target scene: as the limited number of labeled pixels in target scene will affect the graph building of DDNMF, semisupervised learning is adopted in target scene. In details, superpixel segmentation is adopted to generate pseudolabels for some unlabeled pixels, thus more “labeled” pixels can be considered for building better graphs. The effectiveness of SS-DDNMF is verified by experiments on cross-scene HSIs. |
| first_indexed | 2024-12-17T06:40:47Z |
| format | Article |
| id | doaj.art-05af1dc45243429b8cd45a32587fee91 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-17T06:40:47Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-05af1dc45243429b8cd45a32587fee912022-12-21T21:59:51ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352020-01-01133164317810.1109/JSTARS.2020.30006779110759Semisupervised Dual-Dictionary Learning for Heterogeneous Transfer Learning on Cross-Scene Hyperspectral ImagesHong Chen0Minchao Ye1https://orcid.org/0000-0003-3608-7913Ling Lei2Huijuan Lu3Yuntao Qian4https://orcid.org/0000-0002-7418-5891College of Information Engineering, Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, China Jiliang University, Hangzhou, ChinaCollege of Information Engineering, Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, China Jiliang University, Hangzhou, ChinaCollege of Information Engineering, Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, China Jiliang University, Hangzhou, ChinaCollege of Information Engineering, Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, China Jiliang University, Hangzhou, ChinaCollege of Computer Science, Zhejiang University, Hangzhou, ChinaLack of labeled training samples is a big challenge for hyperspectral image (HSI) classification. In recent years, cross-scene classification has become a new research topic. In cross-scene classification, two closely related HSI scenes are considered, one contains adequate labeled samples, namely source scene, while the other one contains only a few labeled samples, namely target scene. The goal of cross-scene classification is utilizing the labeled samples in source scene to benefit the classification in target scene. In most cases, different HSIs are imaged by different sensors, leading to different feature dimensions (numbers of bands) in different scenes. In this situation, heterogeneous transfer learning is demanded. In this article, we propose a heterogeneous transfer learning algorithm namely semisupervised dual-dictionary nonnegative matrix factorization (SS-DDNMF). SS-DDNMF consists of two contributions. 1) Dual-dictionary nonnegative matrix factorization (DDNMF): DDNMF trains two dictionaries for source and target scenes, respectively, aiming at projecting the source and target features to a shared low-dimensional subspace, eliminating the difference between feature spaces. In DDNMF, within-scene and cross-scene graphs are built to maintain the similarities between pixels. 2) Semisupervised learning for target scene: as the limited number of labeled pixels in target scene will affect the graph building of DDNMF, semisupervised learning is adopted in target scene. In details, superpixel segmentation is adopted to generate pseudolabels for some unlabeled pixels, thus more “labeled” pixels can be considered for building better graphs. The effectiveness of SS-DDNMF is verified by experiments on cross-scene HSIs.https://ieeexplore.ieee.org/document/9110759/Cross-scene classificationdual-dictionary learninggraph embeddingheterogeneous transfer learninghyperspectral imagesemisupervised learning |
| spellingShingle | Hong Chen Minchao Ye Ling Lei Huijuan Lu Yuntao Qian Semisupervised Dual-Dictionary Learning for Heterogeneous Transfer Learning on Cross-Scene Hyperspectral Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Cross-scene classification dual-dictionary learning graph embedding heterogeneous transfer learning hyperspectral image semisupervised learning |
| title | Semisupervised Dual-Dictionary Learning for Heterogeneous Transfer Learning on Cross-Scene Hyperspectral Images |
| title_full | Semisupervised Dual-Dictionary Learning for Heterogeneous Transfer Learning on Cross-Scene Hyperspectral Images |
| title_fullStr | Semisupervised Dual-Dictionary Learning for Heterogeneous Transfer Learning on Cross-Scene Hyperspectral Images |
| title_full_unstemmed | Semisupervised Dual-Dictionary Learning for Heterogeneous Transfer Learning on Cross-Scene Hyperspectral Images |
| title_short | Semisupervised Dual-Dictionary Learning for Heterogeneous Transfer Learning on Cross-Scene Hyperspectral Images |
| title_sort | semisupervised dual dictionary learning for heterogeneous transfer learning on cross scene hyperspectral images |
| topic | Cross-scene classification dual-dictionary learning graph embedding heterogeneous transfer learning hyperspectral image semisupervised learning |
| url | https://ieeexplore.ieee.org/document/9110759/ |
| work_keys_str_mv | AT hongchen semisuperviseddualdictionarylearningforheterogeneoustransferlearningoncrossscenehyperspectralimages AT minchaoye semisuperviseddualdictionarylearningforheterogeneoustransferlearningoncrossscenehyperspectralimages AT linglei semisuperviseddualdictionarylearningforheterogeneoustransferlearningoncrossscenehyperspectralimages AT huijuanlu semisuperviseddualdictionarylearningforheterogeneoustransferlearningoncrossscenehyperspectralimages AT yuntaoqian semisuperviseddualdictionarylearningforheterogeneoustransferlearningoncrossscenehyperspectralimages |