SSF-Net: A Spatial–Spectral Features Integrated Autoencoder Network for Hyperspectral Unmixing
Bin Wang, Huizheng Yao, Dongmei Song, Jie Zhang, Han Gao
Abstract
In recent years, deep learning (DL) has received tremendous attention in the field of hyperspectral unmixing (HU) due to its powerful learning capabilities. Particularly, the unsupervised unmixing method based on autoencoder (AE) has become a research hotspot. Most of the current AE unmixing networks mainly focus on information about pixels and their neighborhoods in images. However, they make insufficient use of information about spatial heterogeneity and spectral differences of endmembers in HSI data. To this end, an AE hyperspectral un-mixing network with the name of SSF-Net is proposed for fusing the spatial-spectral features. The network first extracts pseudo-endmember information from the HSI using a regional VCA algorithm. Then, a dual-branch feature fusion module incorporating a spatial-spectral attention mechanism is constructed to make full use of the information in the HSI data, thereby im-proving the network's unmixing performance. It is worth stating that SSF-Net can fuse spatial spectral information and utilize different attention maps to obtain more significant spectral difference information and more discriminative spatial difference information about the scene. Experimental results on synthetic and real datasets demonstrate that the proposed SSF-Net out-performs state-of-the-art unmixing algorithms.