FRFSL: Feature Reconstruction-Based Cross-Domain Few-Shot Learning for Coastal Wetland Hyperspectral Image Classification
IEEE Transactions on Image Processing · 2026 · 35 · 194-207
DOI: 10.1109/tip.2025.3646073 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Qixing Yu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: Shandong Provincial Natural Science Foundation, Postdoctoral Innovation Program of Shandong Province, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Hyperspectral image classification (HSIC) is a valuable method for identifying coastal wetland vegetation, but challenges like environmental complexity and difficulty in distinguishing land cover types make large-scale labeling difficult. Cross-domain few-shot learning (CDFSL) offers a potential solution to limited labeling. Existing CDFSL HSIC methods have made significant progress, but still face challenges like prototype deviation, covariate shifts, and rely on complex domain alignment (DA) methods. To address these issues, a feature reconstruction-based CDFSL (FRFSL) algorithm is proposed. Within FRFSL, a Prototype Calibration Module (PCM) is designed for the prototype deviation, which employs a Bayesian inference-enhanced Gaussian Mixture Model to select reliable query features for prototype reconstruction, aligning the prototypes more closely with the actual distribution. Additionally, a ridge regression closed-form solution is incorporated into the Distance Metric Module (DMM), employing a projection matrix for prototype reconstruction to mitigate covariate shifts between the support and query sets. Features from both source and target domains are reconstructed into dynamic graphs, transforming DA into a graph matching problem guided by optimal transport theory. A novel shared transport matrix implementation algorithm is developed to achieve lightweight and interpretable alignment. Extensive experiments on three self-constructed coastal wetland datasets and one public dataset show that FRFSL outperforms eleven state-of-the-art algorithms. The code will be available at https://github.com/Yqx-ACE/TIP_2025_FRFSL.
Förderung
- Shandong Provincial Natural Science Foundation
- Postdoctoral Innovation Program of Shandong Province
- Fundamental Research Funds for the Central Universities
- Postdoctoral Program of Qingdao
- Innovation Fund Project for Graduate Students of China University of Petroleum
Zitieren
APA
Yu, Q., Li, Z., Xin, Z., Guo, F., Ren, G., Wang, J., & Bi, Z. (2026). FRFSL: Feature Reconstruction-Based Cross-Domain Few-Shot Learning for Coastal Wetland Hyperspectral Image Classification. IEEE Transactions on Image Processing, 35, 194-207. https://doi.org/10.1109/tip.2025.3646073
Vancouver
Yu Q, Li Z, Xin Z, Guo F, Ren G, Wang J, et al. FRFSL: Feature Reconstruction-Based Cross-Domain Few-Shot Learning for Coastal Wetland Hyperspectral Image Classification. IEEE Transactions on Image Processing. 2026;35:194-207. doi:10.1109/tip.2025.3646073
BibTeX
@article{Yu2026,
author = {Yu, Qixing and Li, Zhongwei and Xin, Ziqi and Guo, Fangming and Ren, Guangbo and Wang, Jianbu and Bi, Zhenggang},
title = {FRFSL: Feature Reconstruction-Based Cross-Domain Few-Shot Learning for Coastal Wetland Hyperspectral Image Classification},
journal = {IEEE Transactions on Image Processing},
year = {2026},
volume = {35},
pages = {194--207},
doi = {10.1109/tip.2025.3646073}
}
EUVIMED