A2Former: An Airborne Hyperspectral Crop Classification Framework Based on a Fully Attention-Based Mechanism
Remote Sensing · 09.01.2026 · 18 (2) · 220
DOI: 10.3390/rs18020220 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 09.01.2026. Verfasst von Anqi Kang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Hubei Province.
Abstract (Originalsprache)
Crop classification of farmland is of great significance for crop monitoring and yield estimation. Airborne hyperspectral systems can provide large-format hyperspectral farmland images. However, traditional machine learning-based classification methods rely heavily on handcrafted feature design, resulting in limited representation capability and poor computational efficiency when processing large-format data. Meanwhile, mainstream deep-learning-based hyperspectral image (HSI) classification methods primarily rely on patch-based input methods, where a label is assigned to each patch, limiting the full utilization of hyperspectral datasets in agricultural applications. In contrast, this paper focuses on the semantic segmentation task in the field of computer vision and proposes a novel HSI crop classification framework named All-Attention Transformer (A2Former), which combines CNN and Transformer based on a fully attention-based mechanism. First, a CNN-based encoder consisting of two blocks, the overlap-downsample and the spectral–spatial attention weights block (SSWB) is constructed to extract multi-scale spectral–spatial features effectively. Second, we propose a lightweight C-VIT block to enhance high-dimensional features while reducing parameter count and computational cost. Third, a Transformer-based decoder block with gated-style weighted fusion and interaction attention (WIAB), along with a fused segmentation head (FH), is developed to precisely model global and local features and align semantic information across multi-scale features, thereby enabling accurate segmentation. Finally, a checkerboard-style sampling strategy is proposed to avoid information leakage and ensure the objectivity and accuracy of model performance evaluation. Experimental results on two public HSI datasets demonstrate the accuracy and efficiency of the proposed A2Former framework, outperforming several well-known patch-free and patch-based methods on two public HSI datasets.
Förderung
- Natural Science Foundation of Hubei Province
Zitieren
APA
Kang, A., Li, H., Luo, G., Li, J., & Yin, Z. (2026). A2Former: An Airborne Hyperspectral Crop Classification Framework Based on a Fully Attention-Based Mechanism. Remote Sensing, 18(2), 220. https://doi.org/10.3390/rs18020220
Vancouver
Kang A, Li H, Luo G, Li J, Yin Z. A2Former: An Airborne Hyperspectral Crop Classification Framework Based on a Fully Attention-Based Mechanism. Remote Sensing. 2026;18(2):220. doi:10.3390/rs18020220
BibTeX
@article{Kang2026,
author = {Kang, Anqi and Li, Hua and Luo, Guanghao and Li, Jingyu and Yin, Zhangcai},
title = {A2Former: An Airborne Hyperspectral Crop Classification Framework Based on a Fully Attention-Based Mechanism},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {2},
pages = {220},
doi = {10.3390/rs18020220}
}
EUVIMED