Spectral Unmixing With Multinomial Mixture Kernel and Wasserstein Generative Adversarial Loss
This research provides an incremental improvement in spectral unmixing accuracy for remote sensing and hyperspectral imaging applications, especially when dealing with significant spectral uncertainty.
This paper introduces a new framework for spectral unmixing that uses 1D convolution kernels and a Multinomial Mixture Model to estimate fractions under high spectral uncertainty. The method also incorporates a novel trainable uncertainty term and is optimized using a Wasserstein Generative Adversarial Network. Experiments on real and synthetic datasets demonstrate state-of-the-art performance, particularly on real-world data.
This study proposes a novel framework for spectral unmixing by using 1D convolution kernels and spectral uncertainty. High-level representations are computed from data, and they are further modeled with the Multinomial Mixture Model to estimate fractions under severe spectral uncertainty. Furthermore, a new trainable uncertainty term based on a nonlinear neural network model is introduced in the reconstruction step. All uncertainty models are optimized by Wasserstein Generative Adversarial Network (WGAN) to improve stability and capture uncertainty. Experiments are performed on both real and synthetic datasets. The results validate that the proposed method obtains state-of-the-art performance, especially for the real datasets compared to the baselines. Project page at: https://github.com/savasozkan/dscn.