A Dual-Strategy Learning Framework for Hyperspectral Image Super-Resolution
Hyperspectral image super-resolution (HSI SR) has achieved remarkable success with deep neural networks. Currently, most methods in HSI SR assume a predetermined degradation model during training to synthesize low-resolution images. These methods falter when confronted with HSI exhibiting degradatio...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10891577/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849393886335598592 |
|---|---|
| author | Shuying Li Ruichao Sun San Zhang Qiang Li |
| author_facet | Shuying Li Ruichao Sun San Zhang Qiang Li |
| author_sort | Shuying Li |
| collection | DOAJ |
| description | Hyperspectral image super-resolution (HSI SR) has achieved remarkable success with deep neural networks. Currently, most methods in HSI SR assume a predetermined degradation model during training to synthesize low-resolution images. These methods falter when confronted with HSI exhibiting degradation patterns and their limited flexibility restricts practical application. In addition, these methods focus on the complex network designs for superior performance, which entail high resource consumption and limit their broad application. To address these issues, in this article, we propose a dual-strategy learning framework exploring meta-transfer learning for HSI blind SR. This framework can be applied to any SR network and facilitate performance enhancement. First, we pretrain a three-channel SR model on natural image data to address the issue of insufficient HSI data. Furthermore, we innovatively propose a transfer scheme, which directly applies our pretrained three-channel SR model to HSI, thereby significantly enhancing the spectral fidelity. To enhance the model's performance under specific degradation conditions, we incorporate meta-learning, enabling it to adapt to input images after a few iterations. Besides, we introduce attention-based knowledge distillation to equip our final network with the implicit representation capability of a meta network under a lightweight premise. Extensive experiments on three benchmark datasets demonstrate that the proposed approach outperforms existing methods in various degradations. |
| format | Article |
| id | doaj-art-9f1955f5817c4dc69048cb0159fa727a |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-9f1955f5817c4dc69048cb0159fa727a2025-08-20T03:40:15ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01187480749410.1109/JSTARS.2025.354276610891577A Dual-Strategy Learning Framework for Hyperspectral Image Super-ResolutionShuying Li0https://orcid.org/0000-0002-9641-3584Ruichao Sun1https://orcid.org/0009-0007-6026-1033San Zhang2Qiang Li3https://orcid.org/0000-0002-6736-3389School of Automation, Xi'an University of Posts and Telecommunications, Xi'an, ChinaSchool of Automation, Xi'an University of Posts and Telecommunications, Xi'an, ChinaSchool of Automation, Xi'an University of Posts and Telecommunications, Xi'an, ChinaSchool of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi'an, ChinaHyperspectral image super-resolution (HSI SR) has achieved remarkable success with deep neural networks. Currently, most methods in HSI SR assume a predetermined degradation model during training to synthesize low-resolution images. These methods falter when confronted with HSI exhibiting degradation patterns and their limited flexibility restricts practical application. In addition, these methods focus on the complex network designs for superior performance, which entail high resource consumption and limit their broad application. To address these issues, in this article, we propose a dual-strategy learning framework exploring meta-transfer learning for HSI blind SR. This framework can be applied to any SR network and facilitate performance enhancement. First, we pretrain a three-channel SR model on natural image data to address the issue of insufficient HSI data. Furthermore, we innovatively propose a transfer scheme, which directly applies our pretrained three-channel SR model to HSI, thereby significantly enhancing the spectral fidelity. To enhance the model's performance under specific degradation conditions, we incorporate meta-learning, enabling it to adapt to input images after a few iterations. Besides, we introduce attention-based knowledge distillation to equip our final network with the implicit representation capability of a meta network under a lightweight premise. Extensive experiments on three benchmark datasets demonstrate that the proposed approach outperforms existing methods in various degradations.https://ieeexplore.ieee.org/document/10891577/Blind super-resolution (SR)hyperspectral image (HSI)knowledge distillationmeta learning |
| spellingShingle | Shuying Li Ruichao Sun San Zhang Qiang Li A Dual-Strategy Learning Framework for Hyperspectral Image Super-Resolution IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Blind super-resolution (SR) hyperspectral image (HSI) knowledge distillation meta learning |
| title | A Dual-Strategy Learning Framework for Hyperspectral Image Super-Resolution |
| title_full | A Dual-Strategy Learning Framework for Hyperspectral Image Super-Resolution |
| title_fullStr | A Dual-Strategy Learning Framework for Hyperspectral Image Super-Resolution |
| title_full_unstemmed | A Dual-Strategy Learning Framework for Hyperspectral Image Super-Resolution |
| title_short | A Dual-Strategy Learning Framework for Hyperspectral Image Super-Resolution |
| title_sort | dual strategy learning framework for hyperspectral image super resolution |
| topic | Blind super-resolution (SR) hyperspectral image (HSI) knowledge distillation meta learning |
| url | https://ieeexplore.ieee.org/document/10891577/ |
| work_keys_str_mv | AT shuyingli adualstrategylearningframeworkforhyperspectralimagesuperresolution AT ruichaosun adualstrategylearningframeworkforhyperspectralimagesuperresolution AT sanzhang adualstrategylearningframeworkforhyperspectralimagesuperresolution AT qiangli adualstrategylearningframeworkforhyperspectralimagesuperresolution AT shuyingli dualstrategylearningframeworkforhyperspectralimagesuperresolution AT ruichaosun dualstrategylearningframeworkforhyperspectralimagesuperresolution AT sanzhang dualstrategylearningframeworkforhyperspectralimagesuperresolution AT qiangli dualstrategylearningframeworkforhyperspectralimagesuperresolution |