# Superpixel Contracted Graph-Based Learning for Hyperspectral Image Classification

arXiv: https://arxiv.org/abs/1903.06548 · HTML: https://mlsanity.com/paper/1903.06548/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Mar 2019.

## Built on by (most cited first, 11 of 11)

- [Superpixel-based and Spatially-regularized Diffusion Learning for Unsupervised Hyperspectral Image Clustering](https://mlsanity.com/paper/2312.15447/) (2023)
- [HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation](https://mlsanity.com/paper/2106.03755/) (2021)
- [Hyperspectral Image Classification With Contrastive Graph Convolutional Network](https://mlsanity.com/paper/2205.11237/) (2022)
- [A comprehensive review and new taxonomy on superpixel segmentation](https://mlsanity.com/paper/2409.19179/) (2024)
- [Semi-supervised Superpixel-based Multi-Feature Graph Learning for Hyperspectral Image Data](https://mlsanity.com/paper/2104.13268/) (2021)
- [Graph-Weighted Contrastive Learning for Semi-Supervised Hyperspectral Image Classification](https://mlsanity.com/paper/2503.15731/) (2025)
- [Tree species classification from hyperspectral data using graph-regularized neural networks](https://mlsanity.com/paper/2208.08675/) (2022)
- [Spatial-spectral Hyperspectral Image Classification via Multiple Random Anchor Graphs Ensemble Learning](https://mlsanity.com/paper/2103.13710/) (2021)
- [Bayesian Layer Graph Convolutioanl Network for Hyperspetral Image Classification](https://mlsanity.com/paper/2211.07316/) (2022)
- [Hierarchical Homogeneity-Based Superpixel Segmentation: Application to Hyperspectral Image Analysis](https://mlsanity.com/paper/2407.15321/) (2024)
- [AI-enabled Satellite Edge Computing: A Single-Pixel Feature based Shallow Classification Model for Hyperspectral Imaging](https://mlsanity.com/paper/2601.18560/) (2026)

## Abstract (arXiv)

A central problem in hyperspectral image classification is obtaining high classification accuracy when using a limited amount of labelled data. In this paper we present a novel graph-based framework, which aims to tackle this problem in the presence of large scale data input. Our approach utilises a novel superpixel method, specifically designed for hyperspectral data, to define meaningful local regions in an image, which with high probability share the same classification label. We then extract spectral and spatial features from these regions and use these to produce a contracted weighted graph-representation, where each node represents a region rather than a pixel. Our graph is then fed into a graph-based semi-supervised classifier which gives the final classification. We show that using superpixels in a graph representation is an effective tool for speeding up graphical classifiers applied to hyperspectral images. We demonstrate through exhaustive quantitative and qualitative results that our proposed method produces accurate classifications when an incredibly small amount of labelled data is used. We show that our approach mitigates the major drawbacks of existing approaches, resulting in our approach outperforming several comparative state-of-the-art techniques.