Dual-Stream Attention Network for Hyperspectral Image Unmixing

TL;DR

This paper introduces DSANet, a dual-stream attention network that leverages spatial and spectral information for improved hyperspectral image unmixing, demonstrating superior performance on real datasets.

Contribution

The paper proposes a novel dual-stream attention network with cross-fusion for hyperspectral unmixing, integrating spatial and spectral features effectively.

Findings

Outperforms existing methods on real datasets

Effectively captures spatial-spectral correlations

Enhances unmixing accuracy through cross-fusion attention

Abstract

Hyperspectral image (HSI) contains abundant spatial and spectral information, making it highly valuable for unmixing. In this paper, we propose a Dual-Stream Attention Network (DSANet) for HSI unmixing. The endmembers and abundance of a pixel in HSI have high correlations with its adjacent pixels. Therefore, we adopt a "many to one" strategy to estimate the abundance of the central pixel. In addition, we adopt multiview spectral method, dividing spectral bands into multiple partitions with low correlations to estimate abundances. To aggregate the estimated abundances for complementary from the two branches, we design a cross-fusion attention network to enhance valuable information. Extensive experiments have been conducted on two real datasets, which demonstrate the effectiveness of our DSANet.