EUVIMEDEUVIMED entdecken
Crossref

Domain-Adaptive Mamba for Cross-Scene Hyperspectral Image Classification

Puhong Duan, Shiyu Jin, Xiaotian Lu, Lianhui Liang, Xudong Kang, Antonio Plaza

IEEE Transactions on Image Processing · 2026 · 35 · 1206-1217

DOI: 10.1109/tip.2026.3657209 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Puhong Duan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Science and Technology Inovation Program of Hunan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cross-scene hyperspectral image classification aims to identify a new scene in target domain via learned knowledge from source domain using limited training samples. Existing cross-scene alignment approaches focus on aligning the global feature distribution between the source and target domains while overlooking the fine-grained alignment at different levels. Moreover, they mainly use Transformer architectures to model long-range dependencies across different channels but confront efficiency challenges due to their quadratic complexity, which limits classification performance in unsupervised domain adaptation tasks. To address these issues, a new domain-adaptive Mamba (DAMamba) is proposed for cross-scene hyperspectral image classification. First, a spectral-spatial Mamba is developed to extract high-order semantic features from the input data. Then, a domain-invariant prototype alignment method is proposed from three perspectives, i.e., intra-domain, inter-domain, and mini-batch, to produce reliable pseudo-labels and mitigate the spectral shift between the source and target domains. Finally, a fully connected layer is applied to the aligned features in the target domain to obtain the final classification results. Extensive evaluations across diverse cross-scene datasets demonstrate that our DAMamba outperforms existing state-of-the-art methods in classification accuracy and computing time. The code of this paper is available at https://github.com/PuhongDuan/DAMamba.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Science and Technology Inovation Program of Hunan Province

Zitieren

APA

Duan, P., Jin, S., Lu, X., Liang, L., Kang, X., & Plaza, A. (2026). Domain-Adaptive Mamba for Cross-Scene Hyperspectral Image Classification. IEEE Transactions on Image Processing, 35, 1206-1217. https://doi.org/10.1109/tip.2026.3657209

Vancouver

Duan P, Jin S, Lu X, Liang L, Kang X, Plaza A. Domain-Adaptive Mamba for Cross-Scene Hyperspectral Image Classification. IEEE Transactions on Image Processing. 2026;35:1206-1217. doi:10.1109/tip.2026.3657209

BibTeX
@article{Duan2026,
  author = {Duan, Puhong and Jin, Shiyu and Lu, Xiaotian and Liang, Lianhui and Kang, Xudong and Plaza, Antonio},
  title = {Domain-Adaptive Mamba for Cross-Scene Hyperspectral Image Classification},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {1206--1217},
  doi = {10.1109/tip.2026.3657209}
}
Kostenlos starten →