Oct 2026· Entropy· Vol 28· 0 citations· 51 references
Medicine
TL;DR
Results indicate that AGMNet is particularly effective for abundance recovery while retaining physically interpretable spectral reconstruction, although further improvement of endmember spectral-shape consistency remains necessary.
Abstract
Hyperspectral unmixing aims to recover endmembers and their corresponding abundances from mixed pixels, which is a key task in quantitative hyperspectral remote sensing. Although convolutional neural networks (CNNs) are effective in modeling local spatial–spectral features, their ability to capture long-range spatial dependencies remains limited. Transformers can enhance global feature interactions but typically incur high computational complexity. To address these issues, this study proposes an abundance-guided Mamba network for hyperspectral unmixing, termed AGMNet. Built upon an interpretable autoencoder-based unmixing framework, the proposed method uses CNNs to extract local spatial–spectral features and introduces a lightweight spatial Mamba branch to incorporate whole-image contextual information. Meanwhile, an abundance estimation mechanism with physical constraints and a linear decoder consistent with the linear mixing model are employed to achieve physically interpretable endmember-abundance decomposition. Experiments on three public datasets, namely Samson, Jasper Ridge, and Urban, show that AGMNet provides accurate and stable abundance recovery, achieving the lowest average root mean square error (RMSE) across all three datasets. Its spectral angle distance (SAD) performance is more dataset-dependent: AGMNet obtains the best average SAD on Urban and competitive SAD values on Samson and Jasper Ridge, but it does not consistently achieve the lowest SAD for every endmember. These results indicate that AGMNet is particularly effective for abundance recovery while retaining physically interpretable spectral reconstruction, although further improvement of endmember spectral-shape consistency remains necessary.
Hyperspectral unmixing (HU) is a fundamental task for resolving the mixed pixel problem by decomposing a hyperspectral image (HSI) into constituent endmembers and their corresponding abundances. Although deep-learning-based HU methods have achieved promising performance, most rely on manually designed network architect...
Jing-Ran Wang, Feng-Chao Xiong, Zhiyuan Wen et al.· IEEE Transactions on Geoscie...· 0 citations
SMGNet is proposed, a lightweight spectral-Mamba-guided network that establishes a “spectral leads, spatial follows” paradigm that employs a state space model (Mamba) to efficiently capture global long-range spectral dependencies with linear complexity, while a lightweight Res-CNN preserves intact spatial topology.
Xiao-Yang Meng, Long-Bao Wang, Kai-Jun Jia et al.· IEEE Journal of Selected Top...· 0 citations
An innovative dual-stream spatial-frequency state-space model (SSM) is presented, termed WF-Mamba, for enhanced HU, and an adaptive synergistic fusion (ASF) mechanism is proposed for WF-Mamba to break the bottleneck of rigid feature concatenation.
Lian-Hui Liang, Jin-Rong Chen, Shao-Quan Zhang et al.· IEEE Transactions on Geoscie...· 0 citations
Convolutional neural networks (CNNs) are effective for denoising hyperspectral images (HSIs), but are limited to local feature modeling. Transformers capture global spatial–spectral dependencies but incur high computational and memory costs. State space models (SSMs), such as Mamba, provide an efficient alternative by...
Rahul Kumar, Swarnajyoti Patra, Lorenzo Bruzzone· IEEE Geoscience and Remote S...· 0 citations
The hyperspectral image super-resolution (HSI-SR) enhances spatial resolution while maintaining the information-rich spectral bands in HSI. However, managing the computational overload of spectral bands and capturing the long-range spatial dependencies remains a challenging task. To address these issues, this letter pr...
J. Sandana, S. Deivalakshmi· IEEE Geoscience and Remote S...· 0 citations
This study presents an interpretable stage-wise hyperspectral unmixing framework (I-HyperSU) under fixed endmember priors, which is explicitly decomposed into a fixed endmember matrix, an abundance block, a structural residual refinement block, and a structural residual refinement block.