Fuzzy-MambaHSI: Pixel-Adaptive Fuzzy State-Space Model for Hyperspectral Image Classification
Symmetry · 13.11.2026 · 18 (11) · 1903
DOI: 10.3390/sym18111903 ↗Kurz gefasst
Fachartikel in der Zeitschrift Symmetry, online erschienen am 13.11.2026. Verfasst von Chao Xi und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Anhui Provincial Department of Education.
Abstract (Originalsprache)
Hyperspectral image classification (HSI) faces substantial class-membership uncertainty in mixed-pixel and spectrally confused scenes. The existing Mamba-based methods can model long-range spatial–spectral dependencies with linear complexity, but they usually rely on deterministic feature propagation and do not explicitly represent graded pixel membership during the forward pass. To address this limitation, this paper proposes Fuzzy-MambaHSI, a novel hyperspectral classification framework that embeds learnable fuzzy neural networks into a full-image dense-prediction Mamba backbone. The framework contains three key designs: (1) a fuzzy token perturbation module, which applies soft rule-weighted additive perturbations to tokens at the input of the spatial scan; (2) a fuzzy spatial–spectral fusion module, which replaces global scalar fusion with pixel-wise fuzzy neural network inference; and (3) a training stabilization strategy composed of linear warm-up and rule-center diversity regularization. Experiments with the same settings show that Fuzzy-MambaHSI improves the MambaHSI baseline by 0.96 and 2.92 % in overall accuracy on Pavia University and WHU-Hi-HanChuan, respectively, and yields lower variance in the agricultural scene with stronger spectral confusion. A rule activation analysis shows that different spatial fuzzy rules focus more strongly on homogeneous regions and high-frequency boundary regions, revealing observable differences in pixel membership during the forward pass.
Förderung
- Anhui Provincial Department of Education
Zitieren
APA
Xi, C., Chen, L., & Wang, C. (2026). Fuzzy-MambaHSI: Pixel-Adaptive Fuzzy State-Space Model for Hyperspectral Image Classification. Symmetry, 18(11), 1903. https://doi.org/10.3390/sym18111903
Vancouver
Xi C, Chen L, Wang C. Fuzzy-MambaHSI: Pixel-Adaptive Fuzzy State-Space Model for Hyperspectral Image Classification. Symmetry. 2026;18(11):1903. doi:10.3390/sym18111903
BibTeX
@article{Xi2026,
author = {Xi, Chao and Chen, Long and Wang, Chan},
title = {Fuzzy-MambaHSI: Pixel-Adaptive Fuzzy State-Space Model for Hyperspectral Image Classification},
journal = {Symmetry},
year = {2026},
volume = {18},
number = {11},
pages = {1903},
doi = {10.3390/sym18111903}
}
EUVIMED