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.
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.
Quantum neural networks (QNNs) leverage quantum entanglement and superposition to enable large-scale parallel linear computation, offering a potential solution to the scalability limits of classical deep learning. However, their practical deployment is hampered by two key challenges: the lack of intrinsic nonlinear operations and the barren plateau phenomenon. We propose a quantum convolutional neural network (QCNN) architecture that simultaneously addresses both issues. Nonlinear effects are introduced via orthonormal basis expansions of power series, while barren plateaus are mitigated by directly parameterizing unitary matrices rather than stacking multiple parameterized gates. Our design further incorporates quantum analogs of convolutional kernels and strides for scalable circuit construction. Experiments on MNIST and Fashion-MNIST datasets achieve 99.0% and 88.0% test accuracy, respectively. Consistency between PyTorch-based matrix simulation and Qiskit-based quantum circuit simulation validates the physical fidelity of the model. These results demonstrate a flexible and effective quantum architecture that faithfully integrates classical convolutional mechanisms into a quantum framework, paving the way for practical and expressive QNNs.
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.
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 convolutional neural networks (QCNNs) are emerging as promising models in quantum machine learning, particularly for image classification and computer vision tasks. Recent developments include hybrid classical–quantum architectures, advanced quantum encoding methods, and novel circuit designs that improve data processing on Noisy Intermediate-Scale Quantum (NISQ) devices. However, practical implementation remains challenging due to circuit complexity, gate count, qubit connectivity, and hardware noise, which limit scalability and performance. Consequently, quantum circuit optimization has become essential for reducing resource requirements and improving classification accuracy. This study presents a systematic literature review of 40 research papers published between 2014 and 2025. The review covers QCNNs together with closely related quantum neural network (QNN) models and quantum circuit optimization studies, since circuit-optimization techniques are frequently developed for QNNs more broadly rather than for QCNN architectures in isolation. Within this scope, it examines network architectures, encoding strategies, application domains, and optimization techniques, with particular attention to heuristic and metaheuristic approaches such as genetic algorithms and evolutionary strategies. The findings highlight growing trends in hybrid quantum–classical integration, the widespread adoption of metaheuristic optimization, and the importance of multi-objective frameworks adapted to quantum hardware constraints. Finally, the review identifies key research gaps and future directions for practical QCNN deployment on near-term quantum devices.
This study presents an advanced Quantum Convolutional Neural Network (QCNN) architecture designed to improve classification performance and training stability within the constraints of Noisy Intermediate-Scale Quantum (NISQ) devices. The proposed model incorporates a multi-dimensional quantum feature encoding stage, followed by entanglement-enriched convolutional layers and a refined quantum pooling mechanism. These design innovations increase the circuit’s expressive capacity while reducing susceptibility to barren plateau phenomena, thereby supporting more efficient optimization. Extensive numerical simulations indicate that the model achieves a classification accuracy of 95.2%, with a final loss of 0.24, a low output variance of 0.031, and improved expressibility characterized by a mean fidelity of 0.07. Collectively, these results demonstrate that the enhanced QCNN provides a robust and scalable framework for quantum machine learning tasks suitable for current and near-term quantum hardware.
Quantum Machine Learning (QML) has recently emerged as a highly promising research frontier. Within this domain, Quantum Neural Networks (QNNs),characterized by Variational Quantum Circuits (VQCs) at their core and featuring layers of quantum gates optimized by classical algorithms, have garnered significant attention. However, a rigorous and exhaustive evaluation of their practical performance remains largely incomplete. In this study, we conduct a comprehensive comparative analysis of three prominent hybrid classical-quantum architectures: Quantum Convolutional Neural Networks (QCNN), Quantum Recurrent Neural Networks (QRNN), and Quantum Vision Transformers (QViT), focusing on the critical dimensions of generalization, accuracy, and robustness. Our findings provide novel insights that address previous evaluative gaps. Notably, while these models exhibit exceptional performance on low-feature datasets such as MNIST, their learning efficacy degrades significantly when transitioned to high-feature datasets. Furthermore, convolutional-based models like QCNN appear less effective on high-dimensional data than other machine learning architectures. Additionally, while all models are susceptible to adversarial noise, traditional architectures, such as recurrent and convolutional networks, demonstrate superior resilience. Conversely, in the presence of quantum noise, the transformer-based architecture proves its strength by maintaining high robustness against measurement noise, channel noise, and finite-shot effects, whereas other architectures suffer marked performance declines. These results provide a granular perspective on the current state of the field and underscore the critical importance of tailoring model selection to the constraints of contemporary Noisy Intermediate-Scale Quantum (NISQ) environments.