DEEP DETERMINISTIC INDEPENDENT COMPONENT ANALYSIS FOR HYPERSPECTRAL UNMIXING

We develop a new neural network based independent component analysis (ICA) method by directly minimizing the dependence amongst all extracted components. Using the matrix-based Renyi entropy mutual information, our network can be directly optimized by stochastic gradient descent (SGD), without any variational approximation or adversarial training. As a solid application, we evaluate our ICA in the problem of hyperspectral unmixing (HU) and refute a statement that "ICA does not play a role in unmixing hyperspectral data". Code of our DDICA is available at https://github.com/hongmingli1995/DDICA.