Improved Deep Spectral Convolution Network For Hyperspectral Unmixing With Multinomial Mixture Kernel and Endmember Uncertainty (2018-08-03T00:00:00.000000Z)

TL;DR

The results validate that the proposed method obtains state-of-the-art hyperspectral unmixing performance particularly on the real datasets compared to the baseline techniques.

Abstract

In this study, we propose a novel framework for hyperspectral unmixing by using an improved deep spectral convolution network (DSCN++) combined with endmember uncertainty. DSCN++ is used to compute high-level representations which are further modeled with Multinomial Mixture Model to estimate abundance maps. In the reconstruction step, a new trainable uncertainty term based on a nonlinear neural network model is introduced to provide robustness to endmember uncertainty. For the optimization of the coefficients of the multinomial model and the uncertainty term, Wasserstein Generative Adversarial Network (WGAN) is exploited to improve stability and to capture uncertainty. Experiments are performed on both real and synthetic datasets. The results validate that the proposed method obtains state-of-the-art hyperspectral unmixing performance particularly on the real datasets compared to the baseline techniques.

Authors

G. Akar

3 papers

Savas Özkan

2 papers

TL;DR

Abstract

Authors

References61 items

DAEN: Deep Autoencoder Networks for Hyperspectral Unmixing

Hyperspectral Unmixing via Deep Convolutional Neural Networks

Deep Spectral Convolution Network for Hyperspectral Unmixing

Hyperspectral Unmixing Using Sparsity-Constrained Deep Nonnegative Matrix Factorization With Total Variation

Sliced Wasserstein Distance for Learning Gaussian Mixture Models

A Gaussian Mixture Model Representation of Endmember Variability in Hyperspectral Unmixing

EndNet: Sparse AutoEncoder Network for Endmember Extraction and Hyperspectral Unmixing

Wasserstein Generative Adversarial Networks

Improved Training of Wasserstein GANs

Image-to-Image Translation with Conditional Adversarial Networks

Filling the gaps: Gaussian mixture models from noisy, truncated or incomplete samples

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

WaveNet: A Generative Model for Raw Audio

Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences

Hyperspectral Unmixing With Endmember Variability via Alternating Angle Minimization

Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks

Rethinking the Inception Architecture for Computer Vision

NetVLAD: CNN Architecture for Weakly Supervised Place Recognition

A Spatial Compositional Model for Linear Unmixing and Endmember Uncertainty Estimation

Maximum Likelihood Estimates for Gaussian Mixtures Are Transcendental

Learning with a Wasserstein Loss

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Adam: A Method for Stochastic Optimization

Deep neural networks are easily fooled: High confidence predictions for unrecognizable images

Spatial and Spectral Unmixing Using the Beta Compositional Model

PSO-EM: A Hyperspectral Unmixing Algorithm Based On Normal Compositional Model

Spectral Unmixing via Data-Guided Sparsity

Structured Sparse Method for Hyperspectral Unmixing

Multiple Endmember Spectral Mixture Analysis (MESMA) to map burn severity levels from Landsat images in Mediterranean countries

ImageNet classification with deep convolutional neural networks

Wasserstein active contours

Supervised Nonlinear Spectral Unmixing Using a Postnonlinear Mixing Model for Hyperspectral Imagery

Uncertainty-based learning of Gaussian mixture models from noisy data

Robust Point Set Registration Using Gaussian Mixture Models

Minimal Loss Hashing for Compact Binary Codes

Bilinear models for nonlinear unmixing of hyperspectral images

Non-Linear Spectral Unmixing by Geodesic Simplex Volume Maximization

Blind Spectral Unmixing Based on Sparse Nonnegative Matrix Factorization

Nonlinear unmixing of hyperspectral images using a generalized bilinear model

Nonlinear Spectral Mixture Analysis for Hyperspectral Imagery in an Unknown Environment

Estimating the Number of Endmembers in Hyperspectral Images Using the Normal Compositional Model and a Hierarchical Bayesian Algorithm

Nonlinear mixture model for hyperspectral unmixing

Nonlinear Hyperspectral Mixture Analysis for tree cover estimates in orchards

Optimal Transport: Old and New

Approximating the Kullback Leibler Divergence Between Gaussian Mixture Models

Image quality assessment: from error visibility to structural similarity

Multiscale structural similarity for image quality assessment

Application of the normal compositional model to the analysis of hyperspectral imagery

Evaluation of the potential of Hyperion for fire danger assessment by comparison to the Airborne Visible/Infrared Imaging Spectrometer

Mapping Chaparral in the Santa Monica Mountains Using Multiple Endmember Spectral Mixture Models

On the relationship between spectral unmixing and subspace projection

Bidirectional reflectance spectroscopy: 1. Theory

Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper

A Multilinear Mixing Model for Nonlinear Spectral Unmixing

Linear and nonlinear unmixing in hyperspectral imaging

Dropout: a simple way to prevent neural networks from overfitting

Rectifier Nonlinearities Improve Neural Network Acoustic Models

Product Quantization for Nearest Neighbor Search

Large-Scale Machine Learning with Stochastic Gradient Descent

Spectral unmixing

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names