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

arXiv: https://arxiv.org/abs/1704.07961 · HTML: https://mlsanity.com/paper/1704.07961/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2017.

## Built on by (most cited first, 10 of 10)

- [Multiscale Clustering of Hyperspectral Images Through Spectral-Spatial Diffusion Geometry](https://mlsanity.com/paper/2103.15783/) (2021)
- [Active Diffusion and VCA-Assisted Image Segmentation of Hyperspectral Images](https://mlsanity.com/paper/2204.06298/) (2022)
- [Unsupervised Segmentation of Hyperspectral Remote Sensing Images with Superpixels](https://mlsanity.com/paper/2204.12296/) (2022)
- [Unsupervised Diffusion and Volume Maximization-Based Clustering of Hyperspectral Images](https://mlsanity.com/paper/2203.09992/) (2022)
- [Classification of Hyperspectral Images Using SVM with Shape-adaptive Reconstruction and Smoothed Total Variation](https://mlsanity.com/paper/2203.15619/) (2022)
- [Semi-supervised Change Detection of Small Water Bodies Using RGB and Multispectral Images in Peruvian Rainforests](https://mlsanity.com/paper/2206.09365/) (2022)
- [Generalized Unsupervised Clustering of Hyperspectral Images of Geological Targets in the Near Infrared](https://mlsanity.com/paper/2106.13315/) (2021)
- [Unsupervised Spatial-spectral Hyperspectral Image Reconstruction and Clustering with Diffusion Geometry](https://mlsanity.com/paper/2204.13497/) (2022)
- [Dictionary learning for clustering on hyperspectral images](https://mlsanity.com/paper/2202.00990/) (2022)
- [A distribution-dependent Mumford-Shah model for unsupervised hyperspectral image segmentation](https://mlsanity.com/paper/2203.15058/) (2022)

## Abstract (arXiv)

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.