The growing real-world deployment of computer vision technologies imposes increasingly stringent requirements on the generalization and few-shot adaptation performance of image classification models. While quantum machine learning (QML) has shown considerable promise for image classification tasks, existing hybrid quantum neural networks (HQNNs) consistently exhibit limited generalization ability and weak few-shot learning performance. We investigate the integration of standard W-group averaging into two existing HQNN architectures, HQNN-Parallel and HQNN-Quanv. Each complete input image is transformed by the four elements of the W-group and processed through a shared-parameter feature extractor. The resulting quantum feature vectors or feature maps are averaged before the final classical classification layer. This construction introduces no additional trainable parameters, but requires four transformed-input evaluations per image. The resulting models are denoted as W-HQNN-Parallel and W-HQNN-Quanv, respectively. Systematic experiments on three classic image classification datasets show that the W-HQNN-Parallel model achieves an accuracy of approximately 91.56% on the full FashionMNIST dataset and 73.96% on the full CIFAR-10 dataset respectively, outperforming the original model by around 0.50 and 2.88 percentage points, while also yielding lower test loss than HQNN-Parallel on both datasets. In single-run reduced-data experiments, W-HQNN-Quanv achieved accuracies of 68.83% on MNIST and 64.19% on FashionMNIST, exceeding the corresponding baselines by 9.60 and 6.16 percentage points, respectively. These results provide empirical evidence of the effects of W-group averaging in the two investigated HQNN architectures under the evaluated experimental settings.
The growing real-world deployment of computer vision technologies imposes increasingly stringent requirements on the generalization and few-shot adaptation performance of image classification models. While quantum machine learning (QML) has shown considerable promise for image classification tasks, existing hybrid quantum neural networks (HQNNs) consistently exhibit limited generalization ability and weak few-shot learning performance. We investigate the integration of standard W-group averaging into two existing HQNN architectures, HQNN-Parallel and HQNN-Quanv. Each complete input image is transformed by the four elements of the W-group and processed through a shared-parameter feature extractor. The resulting quantum feature vectors or feature maps are averaged before the final classical classification layer. This construction introduces no additional trainable parameters, but requires four transformed-input evaluations per image. The resulting models are denoted as W-HQNN-Parallel and W-HQNN-Quanv, respectively. Systematic experiments on three classic image classification datasets show that the W-HQNN-Parallel model achieves an accuracy of approximately 91.56% on the full FashionMNIST dataset and 73.96% on the full CIFAR-10 dataset respectively, outperforming the original model by around 0.50 and 2.88 percentage points, while also yielding lower test loss than HQNN-Parallel on both datasets. In single-run reduced-data experiments, W-HQNN-Quanv achieved accuracies of 68.83% on MNIST and 64.19% on FashionMNIST, exceeding the corresponding baselines by 9.60 and 6.16 percentage points, respectively. These results provide empirical evidence of the effects of W-group averaging in the two investigated HQNN architectures under the evaluated experimental settings.
Abstract Image classification, a pivotal task in multiple industries, faces computational challenges due to the burgeoning volume of visual data. This research addresses these challenges by introducing two quantum machine learning models that leverage the principles of quantum mechanics for effective computations. Our first model, a hybrid quantum neural network with parallel quantum circuits, enables the execution of computations even in the noisy intermediate-scale quantum era, where circuits with a large number of qubits are currently infeasible. This model demonstrated a record-breaking classification accuracy of 99.21% on the full MNIST dataset, surpassing the performance of known quantum–classical models, while having eight times fewer parameters than its classical counterpart. Also, the results of testing this hybrid model on a Medical MNIST (classification accuracy over 99%), and on CIFAR-10 (classification accuracy over 82%), can serve as evidence of the generalizability of the model and highlights the efficiency of quantum layers in distinguishing common features of input data. Our second model introduces a hybrid quantum neural network with a Quanvolutional layer, reducing image resolution via a convolution process. The model matches the performance of its classical counterpart, having four times fewer trainable parameters, and outperforms a classical model with equal weight parameters. These models represent advancements in quantum machine learning research and illuminate the path towards more accurate image classification systems.
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 This paper presents a parallel quantum–classical hybrid architecture for image classification that integrates classical feature extraction with parallel quantum processing while maintaining competitive performance and improving parameter efficiency. Low-level and intermediate image features are first extracted by a shared convolutional neural network and then processed by multiple parallel quantum branches. Each branch employs a multilayer variational quantum circuit with a rotation–entanglement–rotation structure. To enhance representation diversity, two encoding-specific strategies are introduced. For amplitude encoding, deterministic spatial permutations generate distinct structural views of the same feature map across branches. For angle encoding, a layer-wise data re-uploading mechanism injects complementary feature subsets into different branches and circuit layers. Heterogeneous entanglement topologies with dynamic routing further diversify qubit interactions without increasing the number of trainable parameters. The measured expectation values from all branches are concatenated and fed into a compact linear classifier. Experiments on MNIST, CIFAR-10, and a thermal image dataset show that the proposed architecture achieves 98.35% accuracy on MNIST and competitive results on the other two datasets, while using substantially fewer parameters in the classification head than a fully classical baseline with the same feature extractor. These results demonstrate that parallel quantum processing combined with structured data embedding can serve as an effective and parameter-efficient decision stage for image classification.
Abstract Quantum Machine Learning (QML) has emerged as a promising paradigm that leverages the principles of quantum mechanics—such as superposition and entanglement—to overcome the limitations of classical machine learning in handling complex, high-dimensional data. However, practical challenges such as limited coherence times of qubits and the integration of quantum circuits with classical architectures have hindered the full realization of QML’s potential. To address these challenges, this paper proposes a novel hybrid architecture, termed the Classical-Quantum Hybrid Convolutional Neural Network (CQHCNN), which integrates quantum-inspired layers into conventional deep learning frameworks. These quantum layers utilize quantum information processing to extract complex features, while the classical components perform feature extraction and classification. This paper evaluates the performance of our model on several benchmark datasets, including MNIST, Fashion-MNIST, CIFAR-10 and COVID-19 Radiography, demonstrating its ability to outperform some other Quantum Convolutional Neural Networks (QCNNs) in terms of many metrics. Experimental results indicate that the hybrid model achieves significant improvements in classification accuracy and computational efficiency, highlighting the potential of quantum-inspired techniques to enhance classical machine learning models.
Abstract In order to explore the possibility of cross-fertilization between quantum computing and neural networks, and to analyse the effects of multiple weight remapping functions on the model performance, this article proposes two hybrid models based on weight remapping: the hybrid quantum neural network (HQNN-WR) and the hybrid quantum convolutional neural network (HQCNN-WR). The HQNN-WR model uses a two-layer fully connected network to process the input features, performs feature transformation by applying multiple weight remapping functions, and subsequently passes the processed features to the quantum neural network for computation, and finally outputs the classification results. The experimental results show that the model significantly improves the classification accuracy on Iris, Wine and Breast datasets and the convergence speed is faster. The HQCNN-WR model integrates convolutional layers, pooling layers, and fully connected layers, and prevents over-fitting through a dropout layer, and exhibits excellent performance in binary classification tasks on MNIST and KMNIST datasets. The model effectively mitigates the over-fitting problem on small sample datasets and enhances the robustness and generalization ability of the model while improving the digit recognition accuracy. By comparing different models, this article also demonstrates their significant effects on the performance of hybrid quantum neural networks, providing a new theoretical basis and experimental support for the optimization and application of quantum machine learning methods.
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.