A Scalable Quantum Non-local Neural Network for Image Classification

TL;DR

This paper introduces QNL-Net, a quantum-classical hybrid neural network that leverages quantum parallelism to efficiently model long-range dependencies in images, achieving high accuracy with fewer qubits.

Contribution

The paper presents a scalable quantum non-local neural network that enhances image classification by utilizing quantum entanglement and parallelism, surpassing existing quantum models in efficiency and accuracy.

Findings

QNL-Net achieves state-of-the-art accuracy in binary image classification.

QNL-Net uses fewer qubits compared to other quantum classifiers.

Simulation results demonstrate improved efficiency and scalability.

Abstract

Non-local operations play a crucial role in computer vision enabling the capture of long-range dependencies through weighted sums of features across the input, surpassing the constraints of traditional convolution operations that focus solely on local neighborhoods. Non-local operations typically require computing pairwise relationships between all elements in a set, leading to quadratic complexity in terms of time and memory. Due to the high computational and memory demands, scaling non-local neural networks to large-scale problems can be challenging. This article introduces a hybrid quantum-classical scalable non-local neural network, referred to as Quantum Non-Local Neural Network (QNL-Net), to enhance pattern recognition. The proposed QNL-Net relies on inherent quantum parallelism to allow the simultaneous processing of a large number of input features enabling more efficient computations in quantum-enhanced feature space and involving pairwise relationships through quantum entanglement. We benchmark our proposed QNL-Net with other quantum counterparts to binary classification with datasets MNIST and CIFAR-10. The simulation findings showcase our QNL-Net achieves cutting-edge accuracy levels in binary image classification among quantum classifiers while utilizing fewer qubits.