Spectral Unmixing via Data-guided Sparsity

Abstract

Hyperspectral unmixing, the process of estimating a common set of spectral bases and their corresponding composite percentages at each pixel, is an important task for hyperspectral analysis, visualization and understanding. From an unsupervised learning perspective, this problem is very challenging---both the spectral bases and their composite percentages are unknown, making the solution space too large. To reduce the solution space, many approaches have been proposed by exploiting various priors. In practice, these priors would easily lead to some unsuitable solution. This is because they are achieved by applying an identical strength of constraints to all the factors, which does not hold in practice. To overcome this limitation, we propose a novel sparsity based method by learning a data-guided map to describe the individual mixed level of each pixel. Through this data-guided map, the ${\ell }_p(0<p<1)$ constraint is applied in an adaptive manner. Such implementation not only meets the practical situation, but also guides the spectral bases toward the pixels under highly sparse constraint. What's more, an elegant optimization scheme as well as its convergence proof have been provided in this paper. Extensive experiments on several datasets also demonstrate that the data-guided map is feasible, and high quality unmixing results could be obtained by our method.

References in corpus (2)

• Effective Spectral Unmixing via Robust Representation and Learning-based Sparsity
• 10,000+ Times Accelerated Robust Subset Selection (ARSS)

Cited by in corpus (23)

• Deep Hyperspectral Unmixing using Transformer Network
• Hyperspectral Unmixing: Ground Truth Labeling, Datasets, Benchmark Performances and Survey
• Hyperspectral Super-Resolution via Interpretable Block-Term Tensor Modeling
• Effective Spectral Unmixing via Robust Representation and Learning-based Sparsity
• Algorithms and Comparisons of Non-negative Matrix Factorization with Volume Regularization for Hyperspectral Unmixing
• SSCU-Net: Spatial-Spectral Collaborative Unmixing Network for Hyperspectral Images
• A spatial compositional model (SCM) for linear unmixing and endmember uncertainty estimation
• A Multibranch Convolutional Neural Network for Hyperspectral Unmixing
• SAWU-Net: Spatial Attention Weighted Unmixing Network for Hyperspectral Images
• Improved Deep Spectral Convolution Network For Hyperspectral Unmixing With Multinomial Mixture Kernel and Endmember Uncertainty
• Robust Tensor Completion Using Transformed Tensor SVD
• Adaptive Multi-Order Graph Regularized NMF with Dual Sparsity for Hyperspectral Unmixing
• Low-rank Tensor Grid for Image Completion
• ICA based on the data asymmetry
• Spectral Unmixing With Multinomial Mixture Kernel and Wasserstein Generative Adversarial Loss
• Endmember Extraction from Hyperspectral Images Using Self-Dictionary Approach with Linear Programming
• Image Smoothing via Unsupervised Learning
• SCA-Net: A Self-Correcting Two-Layer Autoencoder for Hyper-spectral Unmixing
• Hyperspectral Unmixing Network Inspired by Unfolding an Optimization Problem
• Orthogonal Nonnegative Tucker Decomposition
• Tangent Space Based Alternating Projections for Nonnegative Low Rank Matrix Approximation
• Extracting Optimal Solution Manifolds using Constrained Neural Optimization
• Boosting with Lexicographic Programming: Addressing Class Imbalance without Cost Tuning