Hyperspectral Unmixing Using Robust Deep Nonnegative Matrix Factorization

Nonnegative matrix factorization (NMF) and its numerous variants have been extensively studied and used in hyperspectral unmixing (HU). With the aid of the designed deep structure, deep NMF-based methods demonstrate advantages in exploring the hierarchical features of complex data. However, a noise corruption problem commonly exists in hyperspectral data and severely degrades the unmixing performance of deep NMF-based methods when applied to HU. In this study, we propose an l(2,1) norm-based robust deep nonnegative matrix factorization (l(2,1)-RDNMF) for HU, which incorporates an l(2,1) norm into the two stages of the deep structure to achieve robustness. The multiplicative updating rules of l(2,1)-RDNMF are efficiently learned and provided. The efficiency of the presented method is verified in experiments using both synthetic and genuine data.

Automated summary

In this study, a robust deep nonnegative matrix factorization (l(2,1)-RDNMF) based on the l(2,1) norm is proposed for hyperspectral unmixing. The l(2,1)-RDNMF incorporates the l(2,1) norm into the deep structure to achieve robustness. The efficiency and effectiveness of the proposed method are verified through experiments using synthetic and genuine data.