Efficient quantum convolutional neural networks for image classification: overcoming hardware constraints

Abstract While classical convolutional neural networks (CNNs) have revolutionized image classification, the emergence of quantum CNNs (QCNNs) presents new opportunities with high-dimensional transformations that are infeasible for classical CNNs. However, their implementation on current noisy intermediate-scale quantum (NISQ) devices remains challenging due to hardware limitations. In our research, we address this challenge by introducing fragment encoding that significantly reduces the input dimensionality. We show that accuracy improves as the number of qubits increases from 1 to 4 to 16, providing evidence of favorable scaling. Motivated by this, we developed a primitive QCNN architecture with $$\varvec{49}$$ qubits which is sufficient to directly process $$\varvec{28 \times 28}$$ pixel MNIST images, eliminating the need for classical dimensionality reduction pre-processing. Additionally, we propose an automated framework based on expressibility, entanglement, and complexity characteristics to identify the building blocks of QCNNs, parameterized quantum circuits (PQCs). Our approach demonstrates advantages in convergence speed with a similar parameter count compared to both LM-QCNNs and classical CNNs. We validated our experiments on IBM’s Heron r2 quantum processor, achieving $$\varvec{96.08\%}$$ accuracy with approximately $$\varvec{70\%}$$ faster convergence relative to classical CNNs under identical training conditions. Our results show that simple image-classification tasks can be realized on real quantum hardware today.