3D Scalable Quantum Convolutional Neural Networks for Point Cloud Data Processing in Classification Applications

TL;DR

This paper introduces a novel 3D scalable quantum convolutional neural network (sQCNN-3D) designed for point cloud data classification, addressing scalability issues in quantum neural networks using reverse fidelity training.

Contribution

The paper proposes a new 3D scalable QCNN architecture and a reverse fidelity training method to enhance feature extraction in quantum neural networks.

Findings

Achieves high classification accuracy on point cloud data

Demonstrates effective feature diversification with limited qubits

Addresses scalability challenges in quantum neural networks

Abstract

With the beginning of the noisy intermediate-scale quantum (NISQ) era, a quantum neural network (QNN) has recently emerged as a solution for several specific problems that classical neural networks cannot solve. Moreover, a quantum convolutional neural network (QCNN) is the quantum-version of CNN because it can process high-dimensional vector inputs in contrast to QNN. However, due to the nature of quantum computing, it is difficult to scale up the QCNN to extract a sufficient number of features due to barren plateaus. Motivated by this, a novel 3D scalable QCNN (sQCNN-3D) is proposed for point cloud data processing in classification applications. Furthermore, reverse fidelity training (RF-Train) is additionally considered on top of sQCNN-3D for diversifying features with a limited number of qubits using the fidelity of quantum computing. Our data-intensive performance evaluation verifies that the proposed algorithm achieves desired performance.