SNMF-Net: Learning a Deep Alternating Neural Network for Hyperspectral Unmixing

Fengchao Xiong, Jun Zhou, Shuyin Tao, Jianfeng Lu, Yuntao Qian
2021 IEEE Transactions on Geoscience and Remote Sensing  
Hyperspectral unmixing is recognized as an important tool to learn the constituent materials and corresponding distribution in a scene. The physical spectral mixture model is always important to tackle this problem because of its highly illposed nature. In this paper, we introduce a linear spectral mixture model (LMM) based end-to-end deep neural network named as SNMF-Net for hyperspectral unmixing. SNMF-Net shares an alternating architecture and benefits from both model-based methods and
more » ... ng-based methods. On one hand, SNMF-Net is of high physical interpretability as it is built by unrolling Lp sparsity constrained nonnegative matrix factorization (Lp-NMF) model belonging to LMM families. On the other hand, all the parameters and submodules of SNMF-Net can be seamlessly linked with alternating optimization algorithm of Lp-NMF and unmixing problem. This enables to reasonably integrate the prior knowledge on unmixing, optimization algorithm, and sparse representation theory into the network for robust learning so as to improve unmixing. Experimental results on the synthetic and real-world data show the advantages of the proposed SNMF-Net over many state-of-the-art methods.
doi:10.1109/tgrs.2021.3081177 fatcat:njcrtqr5ebg23elgxhzy2czuca