Hybrid Quantum Downsampling Networks

TL;DR

This paper introduces a hybrid quantum downsampling module (HQD) that preserves vital image features better than classical max pooling, leveraging quantum circuits to enhance deep learning models in noisy quantum environments.

Contribution

The paper presents a novel noise-resilient quantum downsampling module that integrates quantum bits and variational circuits to improve image feature preservation in deep learning.

Findings

Models with HQD outperform classical max pooling in CIFAR datasets.

Accuracy improves by approximately 3% on average with HQD.

HQD maintains performance with minimal fluctuation under quantum noise.

Abstract

Classical max pooling plays a crucial role in reducing data dimensionality among various well-known deep learning models, yet it often leads to the loss of vital information. We proposed a novel hybrid quantum downsampling module (HQD), which is a noise-resilient algorithm. By integrating a substantial number of quantum bits (qubits), our approach ensures the key characteristics of the original image are maximally preserved within the local receptive field. Moreover, HQD provides unique advantages in the context of the noisy intermediate-scale quantum (NISQ) era. We introduce a unique quantum variational circuit in our design, utilizing rotating gates including RX, RY, RZ gates, and the controlled-NOT (CNOT) gate to explore nonlinear characteristics. The results indicate that the network architectures incorporating the HQD module significantly outperform the classical structures with max pooling in CIFAR-10 and CIFAR-100 datasets. The accuracy of all tested models improved by an average of approximately 3%, with a maximum fluctuation of only 0.4% under various quantum noise conditions.