Impact of Data Augmentation on QCNNs

TL;DR

This study compares classical CNNs and quantum QCNNs on image datasets, examining the effect of data augmentation, and finds that augmentation does not enhance QCNN performance, prompting further theoretical investigation.

Contribution

It is the first to evaluate data augmentation's impact on QCNNs, revealing that augmentation does not improve QCNN accuracy, unlike in classical CNNs.

Findings

Data augmentation did not improve QCNN performance

QCNNs achieved comparable accuracy without augmentation

Discussion provided on quantum machine learning implications

Abstract

In recent years, Classical Convolutional Neural Networks (CNNs) have been applied for image recognition successfully. Quantum Convolutional Neural Networks (QCNNs) are proposed as a novel generalization to CNNs by using quantum mechanisms. The quantum mechanisms lead to an efficient training process in QCNNs by reducing the size of input from $N$ to $log_2N$. This paper implements and compares both CNNs and QCNNs by testing losses and prediction accuracy on three commonly used datasets. The datasets include the MNIST hand-written digits, Fashion MNIST and cat/dog face images. Additionally, data augmentation (DA), a technique commonly used in CNNs to improve the performance of classification by generating similar images based on original inputs, is also implemented in QCNNs. Surprisingly, the results showed that data augmentation didn't improve QCNNs performance. The reasons and logic behind this result are discussed, hoping to expand our understanding of Quantum machine learning theory.