One-Class Risk Estimation for One-Class Hyperspectral Image Classification

TL;DR

This paper introduces HOneCls, a weakly supervised deep learning model for hyperspectral image one-class classification, effectively handling distribution imbalance and improving classification performance with extensive experiments.

Contribution

It proposes a novel one-class risk estimator integrated into a fully convolutional neural network for hyperspectral images, addressing distribution imbalance issues.

Findings

HOneCls outperforms existing methods in 20 hyperspectral classification tasks.

The risk estimator effectively balances overfitting and underfitting.

Deep learning enhances one-class hyperspectral classification accuracy.

Abstract

Hyperspectral imagery (HSI) one-class classification is aimed at identifying a single target class from the HSI by using only knowing positive data, which can significantly reduce the requirements for annotation. However, when one-class classification meets HSI, it is difficult for classifiers to find a balance between the overfitting and underfitting of positive data due to the problems of distribution overlap and distribution imbalance. Although deep learning-based methods are currently the mainstream to overcome distribution overlap in HSI multiclassification, few studies focus on deep learning-based HSI one-class classification. In this article, a weakly supervised deep HSI one-class classifier, namely, HOneCls, is proposed, where a risk estimator,the one-class risk estimator, is particularly introduced to make the fully convolutional neural network (FCN) with the ability of one class classification in the case of distribution imbalance. Extensive experiments (20 tasks in total) were conducted to demonstrate the superiority of the proposed classifier.