Model-Based Deep Autoencoder Networks for Nonlinear Hyperspectral Unmixing

TL;DR

This paper introduces a model-based autoencoder approach for nonlinear hyperspectral unmixing, leveraging the mixing model's structure to enhance robustness and accuracy in unsupervised unmixing tasks.

Contribution

It proposes a novel model-based autoencoder that incorporates the mixing model structure, improving nonlinear hyperspectral unmixing performance.

Findings

Improved unmixing accuracy on synthetic data

Enhanced robustness in real data experiments

Structured autoencoder benefits in nonlinear scenarios

Abstract

Autoencoder (AEC) networks have recently emerged as a promising approach to perform unsupervised hyperspectral unmixing (HU) by associating the latent representations with the abundances, the decoder with the mixing model and the encoder with its inverse. AECs are especially appealing for nonlinear HU since they lead to unsupervised and model-free algorithms. However, existing approaches fail to explore the fact that the encoder should invert the mixing process, which might reduce their robustness. In this paper, we propose a model-based AEC for nonlinear HU by considering the mixing model a nonlinear fluctuation over a linear mixture. Differently from previous works, we show that this restriction naturally imposes a particular structure to both the encoder and to the decoder networks. This introduces prior information in the AEC without reducing the flexibility of the mixing model. Simulations with synthetic and real data indicate that the proposed strategy improves nonlinear HU.