arrow
Return

Domain-Adaptive Mamba for Cross-Scene Hyperspectral Image Classification

delete2026-01-28
delete0
PRE
AI
段
段普宏 (Puhong Duan)
S
Shiyu Jin
X
Xiaotian Lu
L
Lianhui Liang
X
Xudong Kang
A
Antonio Plaza
DOI:10.1109/TIP.2026.3657209delete
deleteOriginal
deleteShare
deleteSave
Abstract

Abstract

En 中文
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
Keywords:
Hyperspectral images
cross-scene classification
feature alignment

Journal

IEEE Transactions on Image Processing cover
IEEE Transactions on Image Processing
IF:
13.7
Papers:
1.1W
Citations:
8.4W

Organization

U
university of extremadura
Scholars:
115
Papers: 59
Citations: 0
C
China Academy of Space Technology
Scholars:
172
Papers: 114
Citations: 2.5K
H
Hunan University
Scholars:
4.0K
Papers: 1.5K
Citations: 5.9W
G
guangxi university
Scholars:
3.4W
Papers: 1.8W
Citations: 25
researcher View more organizations
Cited Papers

Cited Papers

errShare
errSave
Active Learning for Hyperspectral Image Classification: A Comparative Review
err2022-09-01
err30
PREAI
errThoreau, Romain; Achard, Veronique; Risser, Laurent; Berthelot, Beatrice; Briottet, Xavier
errShare
errSave
Nowhere to Disguise: Spot Camouflaged Objects via Saliency Attribute Transfer
err2023-01-01
err4
PREAI
errZhao, Wenda; Xie, Shigeng; Zhao, Fan; He, You; Lu, Huchuan
errShare
errSave
SVM- and MRF-Based Method for Accurate Classification of Hyperspectral Images
err2010-10-01
err687
errOAAI
errTarabalka, Yuliya; Fauvel, Mathieu; Chanussot, Jocelyn; Benediktsson, Jon Atli
errShare
errSave
Domain-Adversarial Training of Neural Networks
err2017-09-13
err0
PREAI
errYaroslav Ganin; Evgeniya Ustinova; Hana Ajakan; Pascal Germain; Hugo Larochelle; François Laviolette; Mario Marchand; Victor Lempitsky
errShare
errSave
Efficient Swin Transformer for Remote Sensing Image Super-Resolution
err2024-01-01
err0
PREAI
errKang, Xudong; Duan, Puhong; Li, Jier; Li, Shutao
errShare
errSave
researcher View more