Unbalanced Optimal Transport Dictionary Learning for Unsupervised Hyperspectral Image Clustering

TL;DR

This paper introduces an improved method for hyperspectral image clustering that leverages unbalanced Wasserstein barycenters to better handle spectral data variability, noise, and outliers, enhancing unsupervised segmentation accuracy.

Contribution

It proposes using unbalanced Wasserstein barycenters in dictionary learning to improve spectral clustering of hyperspectral images, addressing limitations of balanced approaches.

Findings

Enhanced clustering robustness to noise and outliers

More accurate spectral class separation

Effective unsupervised segmentation results

Abstract

Hyperspectral images capture vast amounts of high-dimensional spectral information about a scene, making labeling an intensive task that is resistant to out-of-the-box statistical methods. Unsupervised learning of clusters allows for automated segmentation of the scene, enabling a more rapid understanding of the image. Partitioning the spectral information contained within the data via dictionary learning in Wasserstein space has proven an effective method for unsupervised clustering. However, this approach requires balancing the spectral profiles of the data, blurring the classes, and sacrificing robustness to outliers and noise. In this paper, we suggest improving this approach by utilizing unbalanced Wasserstein barycenters to learn a lower-dimensional representation of the underlying data. The deployment of spectral clustering on the learned representation results in an effective approach for the unsupervised learning of labels.