Cascaded Dual-directional Cross-attention Transformer Network for hyperspectral imaging classification
Nonlinear Dynamics · 2026-06 · 114 (11)
DOI: 10.1007/s11071-026-12620-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nonlinear Dynamics, online erschienen am 10.06.2026. Verfasst von Songpeng Gong und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: National Science Foundation of China, Hainan Province 2025 International Science and Technology Cooperation RD Project.
Abstract (Originalsprache)
Hyperspectral images possess rich spectral information and spatial characteristics, and traditional classification methods often rely excessively on high-reflectance bands while ignoring crucial spectral information in low-reflectance bands. Under small-sample conditions, this information is often not fully utilized. To solve this problem, this paper proposes a Cascaded Dual-directional Cross-attention Transformer Network (CDCATNet). First, it utilizes 3D convolution to maintain spatial-spectral continuity and designs a cascaded dual cross-attention module to dynamically strengthen the interaction between spatial and spectral features; secondly, it introduces a multi-scale fusion module to capture land cover information at different scales; finally, through tokenized global aggregation and Transformer cross-interaction, it breaks the limitations of local patches to achieve global context modeling. Experiments on the xuzhou, Houston2013, Salinas, and WHU_Hi_HanChuan datasets demonstrate that CDCATNet outperforms existing mainstream methods across multiple evaluation metrics.
Förderung
- National Science Foundation of China
- Hainan Province 2025 International Science and Technology Cooperation RD Project
Zitieren
APA
Gong, S., & Bhatti, U. A. (2026). Cascaded Dual-directional Cross-attention Transformer Network for hyperspectral imaging classification. Nonlinear Dynamics, 114(11). https://doi.org/10.1007/s11071-026-12620-7
Vancouver
Gong S, Bhatti UA. Cascaded Dual-directional Cross-attention Transformer Network for hyperspectral imaging classification. Nonlinear Dynamics. 2026;114(11). doi:10.1007/s11071-026-12620-7
BibTeX
@article{Gong2026,
author = {Gong, Songpeng and Bhatti, Uzair Aslam},
title = {Cascaded Dual-directional Cross-attention Transformer Network for hyperspectral imaging classification},
journal = {Nonlinear Dynamics},
year = {2026},
volume = {114},
number = {11},
doi = {10.1007/s11071-026-12620-7}
}
EUVIMED