MDFFN: Multi-Scale Dual-Aggregated Feature Fusion Network for Hyperspectral Image Classification
Electronics · 07.04.2025 · 14 (7) · 1477
DOI: 10.3390/electronics14071477 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 07.04.2025. Verfasst von Ge Song und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Major Program of Guangdong Provincial Department of Agriculture and Rural Affairs, Guangdong Provincial Education Science Planning Project.
Abstract (Originalsprache)
Employing the multi-scale strategy in hyperspectral image (HSI) classification enables the exploration of complex land-cover structures with diverse shapes. However, existing multi-scale methods still have limitations for fine feature extraction and deep feature fusion, which hinder the further improvement of classification performance. In this paper, we propose a multi-scale dual-aggregated feature fusion network (MDFFN) for both balanced and imbalanced environments. The network comprises two main core modules: a multi-scale convolutional information embedding (MCIE) module and a dual aggregated cross-attention (DACA) module. The proposed MCIE module introduces a multi-scale pooling operation to aggregate local features, which efficiently highlights discriminative spectral–spatial information and especially learns key features in small target samples in the imbalanced environment. Furthermore, the proposed DACA module employs a cross-scale interaction strategy to realize the deep fusion of multi-scale features and designs a dual aggregation mechanism to mitigate the loss of information, which facilitates further spatial–spectral feature enhancement. The experimental results demonstrate that the proposed method outperforms state-of-the-art methods on three classical HSI datasets, proving the superiority of the proposed MDFFN.
Förderung
- National Natural Science Foundation of China
- Major Program of Guangdong Provincial Department of Agriculture and Rural Affairs
- Guangdong Provincial Education Science Planning Project
- Guangdong Provincial Philosophy and Social Science Planning Project
- South China Agricultural University Curriculum Civics Demonstration Project
- Undergraduate Teaching Quality and Teaching Reform Engineering Project of South China Agricultural University
Zitieren
APA
Song, G., Luo, X., Deng, Y., Zhao, F., Yang, X., Chen, J., & Chen, J. (2025). MDFFN: Multi-Scale Dual-Aggregated Feature Fusion Network for Hyperspectral Image Classification. Electronics, 14(7), 1477. https://doi.org/10.3390/electronics14071477
Vancouver
Song G, Luo X, Deng Y, Zhao F, Yang X, Chen J, et al. MDFFN: Multi-Scale Dual-Aggregated Feature Fusion Network for Hyperspectral Image Classification. Electronics. 2025;14(7):1477. doi:10.3390/electronics14071477
BibTeX
@article{Song2025,
author = {Song, Ge and Luo, Xiaoqi and Deng, Yuqiao and Zhao, Fei and Yang, Xiaofei and Chen, Jiaxin and Chen, Jinjie},
title = {MDFFN: Multi-Scale Dual-Aggregated Feature Fusion Network for Hyperspectral Image Classification},
journal = {Electronics},
year = {2025},
volume = {14},
number = {7},
pages = {1477},
doi = {10.3390/electronics14071477}
}
EUVIMED