# CoSpace: Common Subspace Learning from Hyperspectral-Multispectral Correspondences

## TL;DR

This paper introduces CoSpace, a novel framework for joint subspace learning from hyperspectral and multispectral satellite images, improving land cover classification by leveraging shared spectral information.

## Contribution

The paper proposes a new cross-modality feature learning method that aligns hyperspectral and multispectral data in a shared subspace for enhanced classification accuracy.

## Key findings

- CoSpace outperforms existing methods on simulated datasets.
- Shared subspace improves spectral information utilization.
- Method effectively handles trade-offs between coverage and spectral resolution.

## Abstract

With a large amount of open satellite multispectral imagery (e.g., Sentinel-2 and Landsat-8), considerable attention has been paid to global multispectral land cover classification. However, its limited spectral information hinders further improving the classification performance. Hyperspectral imaging enables discrimination between spectrally similar classes but its swath width from space is narrow compared to multispectral ones. To achieve accurate land cover classification over a large coverage, we propose a cross-modality feature learning framework, called common subspace learning (CoSpace), by jointly considering subspace learning and supervised classification. By locally aligning the manifold structure of the two modalities, CoSpace linearly learns a shared latent subspace from hyperspectral-multispectral(HS-MS) correspondences. The multispectral out-of-samples can be then projected into the subspace, which are expected to take advantages of rich spectral information of the corresponding hyperspectral data used for learning, and thus leads to a better classification. Extensive experiments on two simulated HSMS datasets (University of Houston and Chikusei), where HS-MS data sets have trade-offs between coverage and spectral resolution, are performed to demonstrate the superiority and effectiveness of the proposed method in comparison with previous state-of-the-art methods.