Abstract Quantum Convolutional Neural Networks (QCNNs) are a significant quantum machine learning architecture. However, most current designs still mimic the ‘convolution-pooling’ structure of classical CNNs, facing dual challenges of limited feature extraction and inefficient quantum resource usage. To address this, we propose a QCNN based on a hierarchical Ansatz design. Its core is an alternating ‘convolution-entanglement’ structure, which replaces abrupt qubit discarding in traditional pooling with sequential global entanglement layers. This enables non-destructive directional information aggregation, aiming to preserve quantum correlations in data more comprehensively. In the encoding layer, we integrate Principal Component Analysis (PCA) with Instantaneous Quantum Polynomial (IQP) encoding to mitigate the dimensionality mismatch between high-dimensional classical data and limited quantum resources. To systematically evaluate the performance of the proposed architecture, we conducted extensive experiments on the MNIST and Fashion-MNIST datasets. The results demonstrate that: 1) Under various convolutional kernel configurations, our model achieves excellent classification performance, peaking at 99.39% accuracy on MNIST; 2) Even with minimalistic single-qubit rotation gates as the convolutional layer, the model attains 99.14% accuracy using only 16 parameters, demonstrating high parameter efficiency; 3) Crucially, experiments reveal a nonlinear relationship between quantum resources and performance. When qubits exceed a task-specific optimal number, performance declines significantly due to feature space dilution and exacerbated Barren Plateaus. This suggests that, under current quantum hardware conditions, matching resource allocation to task complexity may be more critical than simply scaling up the system. This study offers one potential direction for exploring QCNN architectures. The findings still require further validation across more diverse tasks and in quantum hardware environments closer to practical conditions. We hope this work can provide some useful insights and inform subsequent research.
Abstract Quantum Convolutional Neural Networks (QCNNs) are a significant quantum machine learning architecture. However, most current designs still mimic the ‘convolution-pooling’ structure of classical CNNs, facing dual challenges of limited feature extraction and inefficient quantum resource usage. To address this, we propose a QCNN based on a hierarchical Ansatz design. Its core is an alternating ‘convolution-entanglement’ structure, which replaces abrupt qubit discarding in traditional pooling with sequential global entanglement layers. This enables non-destructive directional information aggregation, aiming to preserve quantum correlations in data more comprehensively. In the encoding layer, we integrate Principal Component Analysis (PCA) with Instantaneous Quantum Polynomial (IQP) encoding to mitigate the dimensionality mismatch between high-dimensional classical data and limited quantum resources. To systematically evaluate the performance of the proposed architecture, we conducted extensive experiments on the MNIST and Fashion-MNIST datasets. The results demonstrate that: 1) Under various convolutional kernel configurations, our model achieves excellent classification performance, peaking at 99.39% accuracy on MNIST; 2) Even with minimalistic single-qubit rotation gates as the convolutional layer, the model attains 99.14% accuracy using only 16 parameters, demonstrating high parameter efficiency; 3) Crucially, experiments reveal a nonlinear relationship between quantum resources and performance. When qubits exceed a task-specific optimal number, performance declines significantly due to feature space dilution and exacerbated Barren Plateaus. This suggests that, under current quantum hardware conditions, matching resource allocation to task complexity may be more critical than simply scaling up the system. This study offers one potential direction for exploring QCNN architectures. The findings still require further validation across more diverse tasks and in quantum hardware environments closer to practical conditions. We hope this work can provide some useful insights and inform subsequent research.
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.
Quantum Convolutional Neural Network (QCNN) has achieved significant success in solving various complex problems, such as quantum many-body physics and image recognition. In comparison to the classical Convolutional Neural Network (CNN) model, the QCNN model requires excellent numerical performance or efficient computational resources to showcase its potential quantum advantages, particularly in classical data processing tasks. In this paper, we propose a computationally resource-efficient QCNN model referred to as RE-QCNN. Specifically, through a comprehensive analysis of the complexity associated with the forward and backward propagation processes in the quantum convolutional layer, our results demonstrate a significant reduction in computational resources required for this layer compared to the classical CNN model. Furthermore, our model is numerically benchmarked on recognizing images from the MNIST and Fashion-MNIST datasets, achieving high accuracy in these multi-class classification tasks.
Image classification plays a vital role in large-scale data analysis, especially in object recognition tasks using advanced Deep Learning (DL) frameworks. However, the growing complexity and computational demands of modern DL models have introduced challenges related to scalability and efficiency. Quantum Computing (QC) has emerged as a promising alternative, capable of addressing these limitations by leveraging the principles of Quantum Machine Learning (QML). However, many existing QML models require a large number of qubits, which poses limitations within the current Noisy Intermediate-Scale Quantum (NISQ) era. This work introduces a novel Adaptive Quantum Convolutional Neural Network (AQCNN) designed for efficient and scalable image classification within the constraints of NISQ devices. Addressing the limitations of existing QML approaches, particularly the high qubit requirements, AQCNN incorporates a resource-efficient quantum convolutional layer that performs localized quantum filtering using parameterized quantum circuits. A classical preprocessing layer encodes input features to reduce qubit load, followed by quantum embedding and hybrid quantum-classical layers that optimize feature extraction and classification performance. The model leverages an adaptive quantum convolution strategy, minimizing quantum gate depth and circuit complexity while preserving critical spatial hierarchies in image data. Evaluated on benchmark datasets, AQCNN achieved 95.88% accuracy on MNIST and 95.68% on FMNIST, outperforming comparable QML architectures. Additionally, the model supports scalable execution through parallel quantum circuit arrays, enabling practical deployment on current quantum hardware. This architecture demonstrates a significant advance in quantum-assisted image classification, balancing performance with qubit and gate efficiency. The integration of adaptive quantum convolution and hybrid processing not only enhances classification accuracy but also provides a viable path forward for deploying QML solutions under realistic hardware constraints.
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 convolutional neural networks (QCNNs) represent a promising approach in quantum machine learning, paving new directions for both quantum and classical data analysis. This approach is particularly attractive due to the absence of the barren plateau problem, a fundamental challenge in training quantum neural networks (QNNs), and its feasibility. However, a limitation arises when applying QCNNs to classical data. The network architecture is most natural when the number of input qubits is a power of two, as this number is reduced by a factor of two in each pooling layer. The number of input qubits determines the dimensions (i.e., the number of features) of the input data that can be processed, restricting the applicability of QCNN algorithms to real-world data. To address this issue, we propose a QCNN architecture capable of handling arbitrary input data dimensions while optimizing the allocation of quantum resources such as ancillary qubits and quantum gates. This optimization is not only important for minimizing computational resources, but also essential in noisy intermediate-scale quantum (NISQ) computing, as the size of the quantum circuits that can be executed reliably is limited. Through numerical simulations, we benchmarked the classification performance of various QCNN architectures across multiple datasets with arbitrary input data dimensions, including MNIST, Landsat satellite, Fashion-MNIST, and Ionosphere. The results validate that the proposed QCNN architecture achieves excellent classification performance while utilizing a minimal resource overhead, providing an optimal solution when reliable quantum computation is constrained by noise and imperfections.
As an emerging research direction in quantum computing, quantum convolutional neural networks provide a promising way to combine quantum feature processing with traditional machine learning algorithms; however, their development is constrained by the scarcity of quantum resources. In this work, we propose a quantum-classical hybrid convolutional neural network model based on quantum convolution kernels. This model employs a multi-data-per-qubit rotation-angle encoding scheme to embed multiple data points into a small number of qubits, aiming to reduce quantum resource consumption and enhance feature extraction for image classification tasks. Its compact structure is designed to extract multidimensional features with fewer qubits and reduced measurement overhead, thereby improving the utilization of limited quantum resources under the considered setting. To evaluate our method, we conducted several experiments to compare our model with existing approaches and to assess performance under varying numbers of qubits, different CNOT gate configurations, and diverse encoding schemes. Experimental results show that the proposed model achieves competitive performance and slightly higher average accuracy than the traditional convolution structure and three existing quantum convolution schemes under a Qiskit Aer noisy simulation environment. This investigation provides a compact design for the structural optimization and low-resource implementation of quantum convolutional neural networks, offering a potential scheme for quantum-assisted image feature extraction.