Emergent Mind

Abstract

Parameterized quantum circuits (PQCs) are essential in many variational quantum algorithms. Quantum convolutional neural networks (QCNNs), which are structurally similar to classical convolutional neural networks, possess the capability to extract informative features and have shown significant effectiveness in image classification tasks. To achieve higher image classification accuracy and reduce the number of training parameters, modifications to the structure of PQCs or hybrid quantum-classical convolutional neural network (HQCCNN) models are typically employed. The image datasets used in these learning models are usually RGB images. We investigate the effects of different color spaces to explore the potential for reducing the resources required for quantum computation. By utilizing a simple HQCCNN model with existing PQCs, we analyze the performance of each channel in various color space images. Experimental results reveal that two channels consistently exhibit higher classification accuracy in images from different color spaces than the third. Specifically, the L channel of LAB color space images achieves superior classification accuracy when employing a more complex PQC. Additionally, PQCs utilizing controlled rotation X-gates outperform those using controlled selection Z-gates in this classification task.

We're not able to analyze this paper right now due to high demand.

Please check back later (sorry!).

Generate a summary of this paper on our Pro plan:

We ran into a problem analyzing this paper.

Newsletter

Get summaries of trending comp sci papers delivered straight to your inbox:

Unsubscribe anytime.