# Hyperspectral Image Classification with Deep Metric Learning and Conditional Random Field

## TL;DR

This paper introduces a novel hyperspectral image classification framework combining deep metric learning with conditional random fields, effectively leveraging spectral features and spatial information to improve accuracy with less training data.

## Contribution

The paper proposes a new integrated approach that combines spectrum-based deep metric learning and CRF for hyperspectral classification, reducing data requirements and enhancing performance.

## Key findings

- Improved classification accuracy on real hyperspectral datasets.
- Reduced training data needs compared to traditional methods.
- Lower computational cost in experiments.

## Abstract

To improve the classification performance in the context of hyperspectral image processing, many works have been developed based on two common strategies, namely the spatial-spectral information integration and the utilization of neural networks. However, both strategies typically require more training data than the classical algorithms, aggregating the shortage of labeled samples. In this letter, we propose a novel framework that organically combines the spectrum-based deep metric learning model and the conditional random field algorithm. The deep metric learning model is supervised by the center loss to produce spectrum-based features that gather more tightly in Euclidean space within classes. The conditional random field with Gaussian edge potentials, which is firstly proposed for image segmentation tasks, is introduced to give the pixel-wise classification over the hyperspectral image by utilizing both the geographical distances between pixels and the Euclidean distances between the features produced by the deep metric learning model. The proposed framework is trained by spectral pixels at the deep metric learning stage and utilizes the half handcrafted spatial features at the conditional random field stage. This settlement alleviates the shortage of training data to some extent. Experiments on two real hyperspectral images demonstrate the advantages of the proposed method in terms of both classification accuracy and computation cost.