Learning Interpretable Deep Disentangled Neural Networks for Hyperspectral Unmixing

Abstract

Although considerable effort has been dedicated to improving the solution to the hyperspectral unmixing problem, non-idealities such as complex radiation scattering and endmember variability negatively impact the performance of most existing algorithms and can be very challenging to address. Recently, deep learning-based frameworks have been explored for hyperspectral umixing due to their flexibility and powerful representation capabilities. However, such techniques either do not address the non-idealities of the unmixing problem, or rely on black-box models which are not interpretable. In this paper, we propose a new interpretable deep learning method for hyperspectral unmixing that accounts for nonlinearity and endmember variability. The proposed method leverages a probabilistic variational deep-learning framework, where disentanglement learning is employed to properly separate the abundances and endmembers. The model is learned end-to-end using stochastic backpropagation, and trained using a self-supervised strategy which leverages benefits from semi-supervised learning techniques. Furthermore, the model is carefully designed to provide a high degree of interpretability. This includes modeling the abundances as a Dirichlet distribution, the endmembers using low-dimensional deep latent variable representations, and using two-stream neural networks composed of additive piecewise-linear/nonlinear components. Experimental results on synthetic and real datasets illustrate the performance of the proposed method compared to state-of-the-art algorithms.

References in corpus (21)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• An Introduction to Variational Autoencoders
• Graph Convolutional Networks for Hyperspectral Image Classification
• Semi-Supervised Learning with Deep Generative Models
• An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixing
• Nonlinear unmixing of hyperspectral images: models and algorithms
• Spectral Variability in Hyperspectral Data Unmixing: A Comprehensive Review
• Hyperspectral unmixing with spectral variability using a perturbed linear mixing model
• Gradient Estimation Using Stochastic Computation Graphs
• Learning Disentangled Representations with Semi-Supervised Deep Generative Models
• Deep Generative Endmember Modeling: An Application to Unsupervised Spectral Unmixing
• Tech Report: A Fast Multiscale Spatial Regularization for Sparse Hyperspectral Unmixing
• A Blind Multiscale Spatial Regularization Framework for Kernel-based Spectral Unmixing
• Hyperspectral Image Unmixing with Endmember Bundles and Group Sparsity Inducing Mixed Norms
• A Gaussian mixture model representation of endmember variability in hyperspectral unmixing
• Unsupervised Unmixing of Hyperspectral Images Accounting for Endmember Variability
• Hyperspectral Unmixing via Deep Autoencoder Networks for a Generalized Linear-Mixture/Nonlinear-Fluctuation Model
• Pathwise Derivatives Beyond the Reparameterization Trick
• A Data Dependent Multiscale Model for Hyperspectral Unmixing With Spectral Variability
• Dynamical Hyperspectral Unmixing with Variational Recurrent Neural Networks