RGB Image Classification with Quantum Convolutional Ansaetze

TL;DR

This paper introduces novel quantum convolutional circuit ansaetze tailored for RGB image classification on NISQ devices, achieving higher accuracy than classical CNNs by effectively extracting intra- and inter-channel information.

Contribution

It presents the first quantum convolutional circuit designs specifically for RGB images, enhancing classification accuracy and exploring the impact of circuit size on learnability.

Findings

Larger quantum circuit ansaetze improve classification accuracy.

Quantum models outperform classical CNNs on CIFAR-10 and MNIST.

Effective extraction of intra- and inter-channel information is crucial.

Abstract

With the rapid growth of qubit numbers and coherence times in quantum hardware technology, implementing shallow neural networks on the so-called Noisy Intermediate-Scale Quantum (NISQ) devices has attracted a lot of interest. Many quantum (convolutional) circuit ansaetze are proposed for grayscale images classification tasks with promising empirical results. However, when applying these ansaetze on RGB images, the intra-channel information that is useful for vision tasks is not extracted effectively. In this paper, we propose two types of quantum circuit ansaetze to simulate convolution operations on RGB images, which differ in the way how inter-channel and intra-channel information are extracted. To the best of our knowledge, this is the first work of a quantum convolutional circuit to deal with RGB images effectively, with a higher test accuracy compared to the purely classical CNNs. We also investigate the relationship between the size of quantum circuit ansatz and the learnability of the hybrid quantum-classical convolutional neural network. Through experiments based on CIFAR-10 and MNIST datasets, we demonstrate that a larger size of the quantum circuit ansatz improves predictive performance in multiclass classification tasks, providing useful insights for near term quantum algorithm developments.