Optimizing Kernel-Target Alignment for cloud detection in multispectral satellite images
Abstract
The optimization of Kernel-Target Alignment (TA) has been recently proposed as a way to reduce the number of hardware resources in quantum classifiers. It allows to exchange highly expressive and costly circuits to moderate size, task oriented ones. In this work we propose a simple toy model to study the optimization landscape of the Kernel-Target Alignment. We find that for underparameterized circuits the optimization landscape possess either many local extrema or becomes flat with narrow global extremum. We find the dependence of the width of the global extremum peak on the amount of data introduced to the model. The experimental study was performed using multispectral satellite data, and we targeted the cloud detection task, being one of the most fundamental and important image analysis tasks in remote sensing.
Cite
@article{arxiv.2306.14515,
title = {Optimizing Kernel-Target Alignment for cloud detection in multispectral satellite images},
author = {Artur Miroszewski and Jakub Mielczarek and Filip Szczepanek and Grzegorz Czelusta and Bartosz Grabowski and Bertrand Le Saux and Jakub Nalepa},
journal= {arXiv preprint arXiv:2306.14515},
year = {2023}
}
Comments
Prepared for IGARSS 2023 Proceedings, 4 pages, 4 figures