Hybrid Quantum-Classical Learning for Multiclass Image Classification

TL;DR

This paper introduces a hybrid quantum-classical neural network architecture that reuses discarded qubit states from NISQ QCNNs to enhance multiclass image classification, demonstrating improved performance on standard datasets.

Contribution

It proposes a novel method to recycle discarded qubit information in QCNNs and combines it with classical layers for better classification accuracy.

Findings

Outperforms lightweight models on MNIST, Fashion-MNIST, and OrganAMNIST.

Recycling discarded qubits improves quantum-classical model performance.

Hybrid architecture effectively integrates quantum and classical processing.

Abstract

This study explores the challenge of improving multiclass image classification through quantum machine-learning techniques. It explores how the discarded qubit states of Noisy Intermediate-Scale Quantum (NISQ) quantum convolutional neural networks (QCNNs) can be leveraged alongside a classical classifier to improve classification performance. Current QCNNs discard qubit states after pooling; yet, unlike classical pooling, these qubits often remain entangled with the retained ones, meaning valuable correlated information is lost. We experiment with recycling this information and combining it with the conventional measurements from the retained qubits. Accordingly, we propose a hybrid quantum-classical architecture that couples a modified QCNN with fully connected classical layers. Two shallow fully connected (FC) heads separately process measurements from retained and discarded qubits, whose outputs are ensembled before a final classification layer. Joint optimisation with a classical cross-entropy loss allows both quantum and classical parameters to adapt coherently. The method outperforms comparable lightweight models on MNIST, Fashion-MNIST and OrganAMNIST. These results indicate that reusing discarded qubit information is a promising approach for future hybrid quantum-classical models and may extend to tasks beyond image classification.