Hyperspectral Image Cross-Domain Classification: A Joint Network of Masked Self-distillation and Confident Learning
文献类型：期刊论文
| 作者 | Li, Haoyu2; Ye, Zhen2; Dong, Xuan2; Li, He1 |
| 刊名 | IMAGE AND GRAPHICS, ICIG 2025, PT III
 |
| 出版日期 | 2026 |
| 卷号 | 16163页码:485-496 |
| 关键词 | hyperspectral image classification domain adaptation masked self-distillation confidence learning |
| ISSN号 | 0302-9743 |
| DOI | 10.1007/978-981-95-3729-7_39 |
| 产权排序 | 2 |
| 文献子类 | Proceedings Paper |
| 英文摘要 | In recent years, unsupervised domain adaptation methods based on deep learning have shown great potential in hyperspectral image cross-domain classification. However, existing methods often face two major challenges: domain distribution differences and data noise interference. To address these issues, this paper proposes a cross-domain classification framework combining confident learning and masked self-distillation (CL-MSD), which constructs an adversarial training network, leveraging the competition between dual classifiers and feature extractors to learn domain-invariant features, and employs a spatial-spectral dual-branch structure to enhance the joint modeling of local and global features. The framework also introduces a masked self-distillation (MSD) module to simulate missing data scenarios and a confident learning (CL) module to filter out low-confidence samples. Experiments on the Houston and Pavia datasets show that the proposed method achieves overall classification accuracies of 83.38% and 93.60%, respectively, demonstrating its effectiveness. |
| URL标识 | 查看原文 |
| WOS研究方向 | Computer Science ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001659276200039 |
| 出版者 | SPRINGER-VERLAG SINGAPORE PTE LTD |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/220932]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Ye, Zhen |
| 作者单位 | 1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China 2.Changan Univ, Sch Elect & Control Engn, Xian, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Li, Haoyu,Ye, Zhen,Dong, Xuan,et al. Hyperspectral Image Cross-Domain Classification: A Joint Network of Masked Self-distillation and Confident Learning[J]. IMAGE AND GRAPHICS, ICIG 2025, PT III,2026,16163:485-496. |
| APA | Li, Haoyu,Ye, Zhen,Dong, Xuan,&Li, He.(2026).Hyperspectral Image Cross-Domain Classification: A Joint Network of Masked Self-distillation and Confident Learning.IMAGE AND GRAPHICS, ICIG 2025, PT III,16163,485-496. |
| MLA | Li, Haoyu,et al."Hyperspectral Image Cross-Domain Classification: A Joint Network of Masked Self-distillation and Confident Learning".IMAGE AND GRAPHICS, ICIG 2025, PT III 16163(2026):485-496. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。