ATN-Hybrid: a hybrid attention network with deterministic-probabilistic mechanism for hyperspectral image classification

Hyperspectral image classification faces significant challenges due to the high dimensionality of spectral data and complex feature relationships between bands. To address the limitations of existing methods, we propose a novel hybrid attention network (ATN-Hybrid) based on a deterministic-probabili...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianshang Liao, Liguo Wang
Format: Article
Language:English
Published: Taylor & Francis Group 2025-08-01
Series:Geo-spatial Information Science
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/10095020.2025.2541876
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849735188454572032
author Jianshang Liao
Liguo Wang
author_facet Jianshang Liao
Liguo Wang
author_sort Jianshang Liao
collection DOAJ
description Hyperspectral image classification faces significant challenges due to the high dimensionality of spectral data and complex feature relationships between bands. To address the limitations of existing methods, we propose a novel hybrid attention network (ATN-Hybrid) based on a deterministic-probabilistic mechanism for hyperspectral image classification. The network employs a dual-branch structure: the deterministic branch generates stable feature weights through explicit channel mapping and normalization, while the probabilistic branch implements temperature-guided adaptive feature selection through a soft attention mechanism. Additionally, we design an adaptive feature fusion strategy with learnable fusion coefficients for dynamic feature optimization. Extensive experimental validation is conducted on four benchmark datasets: Indian Pines, Pavia University, Kennedy Space Center, and Salinas Valley. Experimental results demonstrate that ATN-Hybrid achieves superior performance compared with existing state-of-the-art methods, attaining overall accuracies of 96.01%, 95.23%, 97.37%, and 95.99% on the four datasets, respectively. The method shows particular advantages in both distinguishing classes with similar spectral features and handling limited training samples, achieving favorable results using only 3–9% of the data for training. The hybrid attention mechanism demonstrates strong generalization capabilities in both agricultural and urban scene classification while maintaining stable performance across different spatial resolutions and spectral characteristics.
format Article
id doaj-art-d1d0310a515f4fe4b144dbdd7274ea42
institution DOAJ
issn 1009-5020
1993-5153
language English
publishDate 2025-08-01
publisher Taylor & Francis Group
record_format Article
series Geo-spatial Information Science
spelling doaj-art-d1d0310a515f4fe4b144dbdd7274ea422025-08-20T03:07:37ZengTaylor & Francis GroupGeo-spatial Information Science1009-50201993-51532025-08-0112210.1080/10095020.2025.2541876ATN-Hybrid: a hybrid attention network with deterministic-probabilistic mechanism for hyperspectral image classificationJianshang Liao0Liguo Wang1School of Artificial Intelligence, Guangzhou Maritime University, Guangzhou, ChinaCollege of Information and Communications Engineering, Dalian Minzu University, Dalian, ChinaHyperspectral image classification faces significant challenges due to the high dimensionality of spectral data and complex feature relationships between bands. To address the limitations of existing methods, we propose a novel hybrid attention network (ATN-Hybrid) based on a deterministic-probabilistic mechanism for hyperspectral image classification. The network employs a dual-branch structure: the deterministic branch generates stable feature weights through explicit channel mapping and normalization, while the probabilistic branch implements temperature-guided adaptive feature selection through a soft attention mechanism. Additionally, we design an adaptive feature fusion strategy with learnable fusion coefficients for dynamic feature optimization. Extensive experimental validation is conducted on four benchmark datasets: Indian Pines, Pavia University, Kennedy Space Center, and Salinas Valley. Experimental results demonstrate that ATN-Hybrid achieves superior performance compared with existing state-of-the-art methods, attaining overall accuracies of 96.01%, 95.23%, 97.37%, and 95.99% on the four datasets, respectively. The method shows particular advantages in both distinguishing classes with similar spectral features and handling limited training samples, achieving favorable results using only 3–9% of the data for training. The hybrid attention mechanism demonstrates strong generalization capabilities in both agricultural and urban scene classification while maintaining stable performance across different spatial resolutions and spectral characteristics.https://www.tandfonline.com/doi/10.1080/10095020.2025.2541876Hyperspectral image classificationhybrid attention mechanismdeterministic-probabilistic attentionadaptive feature fusiondeep learning
spellingShingle Jianshang Liao
Liguo Wang
ATN-Hybrid: a hybrid attention network with deterministic-probabilistic mechanism for hyperspectral image classification
Geo-spatial Information Science
Hyperspectral image classification
hybrid attention mechanism
deterministic-probabilistic attention
adaptive feature fusion
deep learning
title ATN-Hybrid: a hybrid attention network with deterministic-probabilistic mechanism for hyperspectral image classification
title_full ATN-Hybrid: a hybrid attention network with deterministic-probabilistic mechanism for hyperspectral image classification
title_fullStr ATN-Hybrid: a hybrid attention network with deterministic-probabilistic mechanism for hyperspectral image classification
title_full_unstemmed ATN-Hybrid: a hybrid attention network with deterministic-probabilistic mechanism for hyperspectral image classification
title_short ATN-Hybrid: a hybrid attention network with deterministic-probabilistic mechanism for hyperspectral image classification
title_sort atn hybrid a hybrid attention network with deterministic probabilistic mechanism for hyperspectral image classification
topic Hyperspectral image classification
hybrid attention mechanism
deterministic-probabilistic attention
adaptive feature fusion
deep learning
url https://www.tandfonline.com/doi/10.1080/10095020.2025.2541876
work_keys_str_mv AT jianshangliao atnhybridahybridattentionnetworkwithdeterministicprobabilisticmechanismforhyperspectralimageclassification
AT liguowang atnhybridahybridattentionnetworkwithdeterministicprobabilisticmechanismforhyperspectralimageclassification