This work presents a study of an implementation of a novel Quantum Convolutional Neural Network (QCNN) for binary classification of images from the Modified National Institute of Standards and Technology (MNIST) dataset. Using a novel architecture inspired by previous QCNN and classical convolutional neural network (CNN) implementations, we use a hierarchical partitioning approach to implement a QCNN circuit that can be approximated and simulated efficiently on a classical machine for a large problem. First, the original image is partitioned such that each process handles a smaller portion of the image, which is encoded into independent states. Then, these partitions merge and combine, resulting in states that contain information from both partitions while halving the number of processes. After repeating this until one process remains, we reduce the dimensionality of the state until a single qubit remains for measurement. Using this approach, we can use multiple processes in parallel to simulate a large QCNN program without the need for exponentially growing hardware requirements as the number of qubits increases. In our work, we use this scheme to train a 128-qubit model, which is impossible to run on any classical supercomputer without the novel architecture. We also explore the impact of this new model architecture on prediction accuracy by training it to perform binary classification on the MNIST dataset with a small number of qubits, and comparing it to a model without partitioning. Our initial findings show that partitioning images into smaller sub-images with this architecture does not degrade the model's performance and sometimes even improves it, likely because it reduces the Barren plateaus issue in the partitioning process.
This work presents a study of an implementation of a novel Quantum Convolutional Neural Network (QCNN) for binary classification of images from the Modified National Institute of Standards and Technology (MNIST) dataset. Using a novel architecture inspired by previous QCNN and classical convolutional neural network (CNN) implementations, we use a hierarchical partitioning approach to implement a QCNN circuit that can be approximated and simulated efficiently on a classical machine for a large problem. First, the original image is partitioned such that each process handles a smaller portion of the image, which is encoded into independent states. Then, these partitions merge and combine, resulting in states that contain information from both partitions while halving the number of processes. After repeating this until one process remains, we reduce the dimensionality of the state until a single qubit remains for measurement. Using this approach, we can use multiple processes in parallel to simulate a large QCNN program without the need for exponentially growing hardware requirements as the number of qubits increases. In our work, we use this scheme to train a 128-qubit model, which is impossible to run on any classical supercomputer without the novel architecture. We also explore the impact of this new model architecture on prediction accuracy by training it to perform binary classification on the MNIST dataset with a small number of qubits, and comparing it to a model without partitioning. Our initial findings show that partitioning images into smaller sub-images with this architecture does not degrade the model's performance and sometimes even improves it, likely because it reduces the Barren plateaus issue in the partitioning process.
Convolutional Neural Networks (CNNs) are extensively utilized for image classification due to their ability to exploit data correlations effectively. However, traditional CNNs encounter several challenges, including limitations in accuracy improvement, computational efficiency, explain ability, and generalization. As data dimensionality or model complexity increases, CNNs often become more difficult to train efficiently, leading to slower processing times. To overcome these challenges, Quantum Convolutional Neural Networks (QCNNs) offer a promising quantum-based approach to enhance existing models, particularly by improving training efficiency and reducing processing times. This paper provides a comparative analysis of classical CNNs and a novel quantum circuit architecture tailored for image-based tasks. The analysis emphasizes the adaptability and potential of quantum circuits to enhance feature extraction, recognition accuracy, and processing efficiency.We applied various QCNN architectures to the Chinese-MNIST dataset and compared their performance with traditional CNN models. Although QCNNs achieved slightly lower accuracy, they demonstrated significantly greater stability. These findings high- light QCNNs’ potential to overcome the computational limitations of conventional deep learning, offering a promising pathway for quantum-enhanced solutions in computer vision. Future work will focus on refining quantum circuit designs, developing hybrid quantum-classical models, and extending QCNN applications to larger and more diverse datasets.
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.
Classical convolutional neural networks (CNNs) have achieved notable success in image classification but face challenges in scalability, interpretability, and computational cost. With the growing availability of Noisy Intermediate-Scale Quantum (NISQ) devices, hybrid quantum-classical models offer a promising alternative by leveraging quantum parallelism and entanglement. In this work, we present a hybrid Quantum Convolutional Neural Network (QCNN) that integrates quantum convolutional layers into classical image classification pipeline for the MNIST dataset. Our architecture features a modular, low-depth Quantum Kernel Convolution (QKC) design suitable for near-term hardware. We implement the system using Qiskit and evaluate in terms of classification accuracy, circuit efficiency, and integration feasibility. Our results demonstrate that (i) the hybrid QCNN achieves similar accuracy to classical models while reducing the number of classical parameters, and (ii) quantum layers can successfully perform dimensionality reduction through entanglement-based pooling. This study highlights the potential of hybrid QCNN as a practical quantum-enhanced model for real-world image recognition tasks.
Quantum machine learning is emerging as a promising frontier at the intersection of quantum computing and Artificial Intelligence, offering potential gains in speed, efficiency, and robustness. In this paper, a hybrid Quantum Convolutional Neural Network (QCNN) architecture is presented for visual pattern recognition tasks, leveraging quantum superposition and entanglement for enhanced feature extraction. Unlike previous studies that focus on small-scale or simplified datasets, this study systematically evaluates QCNNs across multiple benchmark datasets and provides a direct comparison with classical CNNs, highlighting practical quantum advantages such as parameter efficiency and noise-resilience. The proposed approach encodes classical image data from benchmark datasets, including70K28×28grayscale images from MNIST and FashionMNIST, and60Kdownsampled grayscale CIFAR-10 images, into quantum states using amplitude encoding, followed by hierarchical quantum convolution and pooling layers implemented via parametrised quantum circuits (PQCs). The model culminates in a classical dense layer for final classification. Experimental results demonstrate that the QCNN achieves competitive performance on low-dimensional grayscale datasets with 93.2 % accuracy on MNIST and 88.5% on Fashion MNIST, though it underperforms on more complex datasets like CIFAR-10 with 67.8 % accuracy due to current quantum hardware limitations. While not yet surpassing classical CNNs in raw accuracy, the proposed QCNN exhibits notable parameter efficiency, noise resilience, and theoretical potential for energy-efficient computation, highlighting its promise for future applications as quantum technologies mature.
This study introduces a scalable and noise-tolerant quantum convolutional neural network (QCNN) architecture for large-scale image classification using Noisy Intermediate-Scale Quantum (NISQ) devices. The architecture employs a hybrid quantum-classical approach; classical data from the MNIST dataset are initially preprocessed before being converted into quantum states using angle encoding and superposition methods. The QCNN consists of Quantum Convolution Layers and classical layers of pooling and variational classification, which extract features from input images and classify them. To mitigate the impact of noise and hardware limitations, we applied a pruning-based optimization technique that reduces the circuit depth from 400 to 130 and the gate count from 900 to 280 while maintaining high accuracy (up to 0.94). The results also demonstrate an approximately 80% decrease in loss (from 1.20 to 0.25) and approximately 75% decrease in mean square error (from 0.50 to 0.12), and an increase in robustness (from 0.85 to 0.89). Finally, we found that our optimized QCNN has better classification performance than traditional QCNNs, and comparable performance to classical CNNs.
The domain of image classification has been seen to be dominated by high-performing deep-learning (DL) architectures. However, the success of this field, as seen over the past decade, has resulted in the complexity of modern methodologies scaling exponentially, commonly requiring millions of parameters. Quantum computing (QC) is an active area of research aimed toward greatly reducing problems of complexity faced in classical computing. With growing interest toward quantum machine learning (QML) for applications of image classification, many proposed algorithms require usage of numerous qubits. In the noisy intermediate-scale quantum (NISQ) era, these circuits may not always be feasible to execute effectively; therefore, we should aim to use each qubit as effectively and efficiently as possible, before adding additional qubits. This article proposes a new single-qubit-based deep quantum neural network for image classification that mimics traditional convolutional neural network (CNN) techniques, resulting in a reduced number of parameters compared with previous works. Our aim is to prove the concept of the initial proposal by demonstrating classification performance of the single-qubit-based architecture, as well as to provide a tested foundation for further development. To demonstrate this, our experiments were conducted using various datasets including MNIST, Fashion-MNIST, and ORL face datasets. To further our proposal in the context of the NISQ era, our experiments were intentionally conducted in noisy simulation environments. Initial test results appear promising, with classification accuracies of 94.6%, 89.5%, and 82.5% achieved on the subsets of MNIST, FMNIST, and ORL face datasets, respectively. In addition, proposals for further investigation and development were considered, where it is hoped that these initial results can be improved.