Quantum Pointwise Convolution: A Flexible and Scalable Approach for Neural Network Enhancement

TL;DR

This paper introduces Quantum Pointwise Convolution, a novel quantum neural network layer that enhances feature integration and efficiency using quantum circuits, with promising results on image classification datasets.

Contribution

It presents a new quantum convolutional layer with optimizations like amplitude encoding and weight sharing, improving efficiency and applicability in quantum neural networks.

Findings

Competitive performance on FashionMNIST and CIFAR10 datasets

Enhanced efficiency through amplitude encoding and weight sharing

Broader applicability in CNN-based models

Abstract

In this study, we propose a novel architecture, the Quantum Pointwise Convolution, which incorporates pointwise convolution within a quantum neural network framework. Our approach leverages the strengths of pointwise convolution to efficiently integrate information across feature channels while adjusting channel outputs. By using quantum circuits, we map data to a higher-dimensional space, capturing more complex feature relationships. To address the current limitations of quantum machine learning in the Noisy Intermediate-Scale Quantum (NISQ) era, we implement several design optimizations. These include amplitude encoding for data embedding, allowing more information to be processed with fewer qubits, and a weight-sharing mechanism that accelerates quantum pointwise convolution operations, reducing the need to retrain for each input pixels. In our experiments, we applied the quantum pointwise convolution layer to classification tasks on the FashionMNIST and CIFAR10 datasets, where our model demonstrated competitive performance compared to its classical counterpart. Furthermore, these optimizations not only improve the efficiency of the quantum pointwise convolutional layer but also make it more readily deployable in various CNN-based or deep learning models, broadening its potential applications across different architectures.