# Unsupervised Clustering and Active Learning of Hyperspectral Images with Nonlinear Diffusion

## TL;DR

This paper introduces an unsupervised spectral-spatial diffusion learning method for hyperspectral image segmentation that effectively handles high dimensionality and noise, with an active learning variation that improves clustering accuracy with minimal labeled data.

## Contribution

The paper proposes a novel nonlinear diffusion-based clustering and segmentation method for hyperspectral images, incorporating spectral and spatial information, and introduces an active learning variant for enhanced performance.

## Key findings

- Outperforms state-of-the-art hyperspectral segmentation techniques
- Robust to parameter choices and noise
- Low computational complexity

## Abstract

The problem of unsupervised learning and segmentation of hyperspectral images is a significant challenge in remote sensing. The high dimensionality of hyperspectral data, presence of substantial noise, and overlap of classes all contribute to the difficulty of automatically clustering and segmenting hyperspectral images. We propose an unsupervised learning technique called spectral-spatial diffusion learning (DLSS) that combines a geometric estimation of class modes with a diffusion-inspired labeling that incorporates both spectral and spatial information. The mode estimation incorporates the geometry of the hyperspectral data by using diffusion distance to promote learning a unique mode from each class. These class modes are then used to label all points by a joint spectral-spatial nonlinear diffusion process. A related variation of DLSS is also discussed, which enables active learning by requesting labels for a very small number of well-chosen pixels, dramatically boosting overall clustering results. Extensive experimental analysis demonstrates the efficacy of the proposed methods against benchmark and state-of-the-art hyperspectral analysis techniques on a variety of real datasets, their robustness to choices of parameters, and their low computational complexity.