Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

International Joint Conference on Neural Networks (IJCNN)

Quantum for Representation: Circuit-Based Attention Mechanism for Hyperspectral Feature Learning

Yitong Shang, Haosen Yang, Duo Li, Yonggang Wang

Published Jun 1, 2026• 0 citations
Publisher

Abstract

Hyperspectral Image (HSI) classification requires the effective integration of spectral signatures and spatial contextual information. While classical Deep Learning models like Convolutional Neural Networks and Transformers have achieved remarkable success, they often demand significant computational resources. Quantum Machine Learning offers a promising alternative with its high-dimensional Hilbert space and entanglement capabilities, yet existing quantum approaches for HSI often rely on generic circuit designs that lack domain-specific inductive biases. In this paper, we propose a novel Quantum Spatial Attention Network (QSAN). We design a specific spatial feature extractor that decomposes HSI patches into "Core" (center pixel) and "Context" (surrounding average) components. These components are encoded into two distinct quantum registers (heads). We introduce a circuit-based attention mechanism utilizing Controlled-Rotation gates to model the interaction between the core and context qubits, effectively simulating the query-key mechanism in classical attention. Furthermore, we employ highorder Pauli-Z correlation measurements to explicitly capture the spatial-spectral consistency. Experimental results on dataset demonstrate that our proposed QSAN achieves competitive classification accuracy with significantly fewer trainable parameters compared to classical counterparts, validating the potential of quantum circuits for efficient HSI representation learning.

DOI
10.1109/ijcnn69854.2026.11729990

Related papers

QueenNet: Quantum-Enhanced Neural Network for Hyperspectral Image Classification

Qingwang Wang, Shunyuan Wang, Yinxing Zhang +3 more

Hyperspectral image (HSI) classification is a critical task in the field of remote sensing. Existing deep learning models have made significant progress in HSI classification, but often suffer from parameter redundancy and insufficient noise robustness when handling the high-dimensional nonlinear spatial-spectral information. Recently, quantum computing have garnered significant attention in modeling higher-order correlations with remarkable parameter efficiency. Inspired by this, we propose a QUantum-Enhanced nEural Network (QueenNet) for HSI classification. QueenNet comprises three primary modules, including Quantum Encoding (QE), Quantum Convolution (QC), and Quantum Measurement (QM). Specifically, QE maps HSI into an hyper high-dimensional Hilbert space, encoding it as a quantum states. QC performs HSI feature extraction and transformation using quantum circuits composed of parameterized quantum gate sequences, which effectively enhances the model's ability to capture joint spatial-spectral features while suppressing spectral noise. QM introduces nonlinear feature extraction operations and decodes the HSI features of quantum states back into classic interpretable probability distributions for classification. QueenNet effectively alleviate the limitations of existing HSI classification deep learning models by leveraging the high-dimensional feature representation advantages of quantum computing, introducing a novel paradigm to HSI classification. Extensive experiments on three benchmark datasets demonstrate that QueenNet achieves an order-of-magnitude reduction in model parameters while surpassing the classification performance of state-of-the-art methods.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing•Jan 1, 2026•3 citations

QPCNet: A hybrid quantum positional encoding and channel attention network for image classification

Yaochong Li, ZuAo Cheng, YiFan Zhang +1 more

Abstract Quantum-classical hybrid neural networks have recently emerged as a prominent research direction, combining the expressive power of quantum computing with the robustness and scalability of classical deep learning. These models have demonstrated significant potential, especially in image classification scenarios. However, existing hybrid architectures often fail to jointly model spatial and channel-wise features, which may constrain their representational capacity. In this work, we propose a novel quantum-enhanced convolutional neural network architecture that integrates Quantum Positional Encoding (QPE) and Quantum Channel Attention (QCA) mechanisms. These components respectively enhance spatial and channel-wise feature representations, while ensuring compatibility with conventional training pipelines. Experiments on the MNIST and Fashion-MNIST datasets demonstrate that the proposed model consistently outperforms classical CNN baselines in classification accuracy. Furthermore, experiments on the challenging CIFAR-10 dataset further validate the competitive performance of the proposed model, highlighting its strong generalization capability. These findings underscore the practical value of integrating quantum mechanisms into deep learning and emphasize their potential to advance intelligent visual recognition systems.

Physica Scripta•Oct 24, 2025•4 citations

HQCNN: a hybrid quantum-classical neural network with Fourier-inspired quantum attention for medical image classification

Shahjalal Khan, Jahid Karim Fahim, Pintu Chandra Paul +5 more

Medical image classification is a critical component of modern healthcare; however, accurate diagnosis remains challenging due to limited annotated datasets, class imbalance, and the high dimensionality of medical imaging data. To address these challenges, a hybrid quantum-classical neural network (HQCNN) is proposed, integrating classical deep learning with variational quantum learning for medical image classification. The proposed architecture combines a five-layer convolutional neural network (CNN) for hierarchical feature extraction with a lightweight 4-qubit variational quantum circuit (VQC) incorporating quantum state encoding, superposition and entanglement mechanisms, and a quantum attention-Fourier (QAF) module. This hybrid design aims to improve nonlinear feature representation and quantum parameter efficiency while maintaining a shallow quantum circuit suitable for noisy intermediate-scale quantum (NISQ)-era constraints. Experimental evaluation on six MedMNIST benchmark datasets demonstrated competitive performance across both binary and multi-class classification tasks. HQCNN achieved 98.88% accuracy on the binary subset of PathMNIST (classes 0 vs. 1), 97.61% accuracy on the multi-class OrganAMNIST dataset, and 86.29% accuracy on BreastMNIST. Comparative experiments and statistical analyses demonstrated consistent improvements over the controlled BHQNN baseline, while component-wise ablation studies showed that the QAF module, superposition and entanglement mechanisms, and expressive parameterized rotations contributed to classification performance in a complementary and dataset-dependent manner. Moreover, HQCNN reduced the number of trainable quantum parameters by approximately 55.6% compared with the baseline hybrid quantum neural network (BHQNN). Noise-aware simulations further showed that the model retained relatively stable predictive performance under moderate depolarizing noise, supporting further evaluation under near-term quantum computing conditions. Overall, the results demonstrate that HQCNN provides a parameter-efficient hybrid quantum-classical framework for medical image classification and offers a promising foundation for further investigation of quantum-enhanced medical image analysis.

International Journal of Advanced Technology and Engineering Exploration•Aug 31, 2026•0 citations

Quantum Parameterized Self-Attention Network for Image Classification

Wenwei Zhang, Jintao Wang, Tianyu Ye +1 more

Transformer now underpins modern AI as its core infrastructure. Its defining capability-dynamically focusing on the most relevant information in complex inputs-is bounded above by the self-attention scoring function. Quantum computing, with its superposition, entanglement, and probabilistic outputs, offers a fundamentally distinct computational framework for exploring beyond the design constraints of classical scoring functions. While quantum attention mechanisms have shown initial promise, existing works remain largely confined to redefining feature similarity measures, leaving the systematic use of parameterized quantum circuits (PQCs) as scoring functions largely unexplored; a substantial portion of existing schemes further rely on purely quantum architectures, precluding effective encoding of high-dimensional image inputs in the Noisy Intermediate-Scale Quantum era. We propose the Quantum Parameterized Self-Attention Network (QPSAN), implementing the self-attention scoring function via PQCs with only 5 trainable quantum parameters per layer. QPSAN computes query-key attention scores through quantum state encoding and joint measurement, yielding naturally bounded outputs without the explicit scaling of classical dot-product attention. We further establish a theoretical framework of the mathematical properties of this scoring function, demonstrating its potential to capture complex nonlinear query-key interactions, and quantifying the structural constraints of the encoding layer via effective degrees of freedom analysis. Experiments on four vision datasets show that QPSAN significantly outperforms the Vision Transformer (ViT) baseline, with the quantum representational advantage amplifying as data complexity increases. Ablation studies indicate that the performance gains may stem from the structural inductive bias of the quantum circuit rather than from parameter scale.

quant-pharXiv:2605.25365•May 26, 2026•1 citation

Efficient Gate-Encoded Quantum Convolutional Neural Network with Channel Attention for Image Classification

Yiling Lin, G. Yu, Tianze Zhu +1 more

This paper presents an improved Quantum Convolutional Neural Network (QCNN) architecture that overcomes key limitations of current quantum-classical hybrid models for image classification. To address challenges in expressivity and feature extraction on noisy intermediate-scale quantum (NISQ) devices, we propose two key innovations: (1) Gate Encoding Optimization, which reduces quantum bit (qubit) usage while retaining spatial information, and (2) Quantum Channel Attention (QCA), a novel attention mechanism tailored for hybrid QCNNs which utilizes measurement-driven feedback to capture inter-channel dependencies. Evaluated on the MNIST dataset, our model achieves 95.68 % accuracy—on par with classical CNNs (95.73 %) and significantly better than a baseline QCNN (93.23%)—while reducing parameters by 49.6 %. These results demonstrate the proposed model's effectiveness and practicality for quantum machine learning in the NISQ era.

IEEE International Conference on Tools with Artificial Intelligence (ICTAI)•Nov 3, 2025•0 citations

Quantum-Enhanced Attention Mechanism in NLP: A Hybrid Classical-Quantum Approach

S. M. Yousuf Iqbal Tomal, Abdullah Al Shafin, Bhattacharjee, Debojit +2 more

Recent advances in quantum computing have opened new pathways for enhancing deep learning architectures, particularly in domains characterized by high-dimensional and context-rich data such as natural language processing (NLP). In this work, we present a hybrid classical-quantum Transformer model that integrates a quantum-enhanced attention mechanism into the standard classical architecture. By embedding token representations into a quantum Hilbert space via parameterized variational circuits and exploiting entanglement-aware kernel similarities, the model captures complex semantic relationships beyond the reach of conventional dot-product attention. We demonstrate the effectiveness of this approach across diverse NLP benchmarks, showing improvements in both efficiency and representational capacity. The results section reveal that the quantum attention layer yields globally coherent attention maps and more separable latent features, while requiring comparatively fewer parameters than classical counterparts. These findings highlight the potential of quantum-classical hybrid models to serve as a powerful and resource-efficient alternative to existing attention mechanisms in NLP.

arXiv:2501.15630•Jan 26, 2025•14 citations
Hyperspectral Image (HSI) classification requires the effective integration of spectral signatures and spatial contextual information. While classical Deep Learning models like Convolutional Neural Networks and Transformers have achieved remarkable success, they often demand significant computational resources. Quantum Machine Learning offers a promising alternative with its high-dimensional Hilbert space and entanglement capabilities, yet existing quantum approaches for HSI often rely on generic circuit designs that lack domain-specific inductive biases. In this paper, we propose a novel Quantum Spatial Attention Network (QSAN). We design a specific spatial feature extractor that decomposes HSI patches into "Core" (center pixel) and "Context" (surrounding average) components. These components are encoded into two distinct quantum registers (heads). We introduce a circuit-based attention mechanism utilizing Controlled-Rotation gates to model the interaction between the core and context qubits, effectively simulating the query-key mechanism in classical attention. Furthermore, we employ highorder Pauli-Z correlation measurements to explicitly capture the spatial-spectral consistency. Experimental results on dataset demonstrate that our proposed QSAN achieves competitive classification accuracy with significantly fewer trainable parameters compared to classical counterparts, validating the potential of quantum circuits for efficient HSI representation learning.
Hyperspectral image (HSI) classification is a critical task in the field of remote sensing. Existing deep learning models have made significant progress in HSI classification, but often suffer from parameter redundancy and insufficient noise robustness when handling the high-dimensional nonlinear spatial-spectral information. Recently, quantum computing have garnered significant attention in modeling higher-order correlations with remarkable parameter efficiency. Inspired by this, we propose a QUantum-Enhanced nEural Network (QueenNet) for HSI classification. QueenNet comprises three primary modules, including Quantum Encoding (QE), Quantum Convolution (QC), and Quantum Measurement (QM). Specifically, QE maps HSI into an hyper high-dimensional Hilbert space, encoding it as a quantum states. QC performs HSI feature extraction and transformation using quantum circuits composed of parameterized quantum gate sequences, which effectively enhances the model's ability to capture joint spatial-spectral features while suppressing spectral noise. QM introduces nonlinear feature extraction operations and decodes the HSI features of quantum states back into classic interpretable probability distributions for classification. QueenNet effectively alleviate the limitations of existing HSI classification deep learning models by leveraging the high-dimensional feature representation advantages of quantum computing, introducing a novel paradigm to HSI classification. Extensive experiments on three benchmark datasets demonstrate that QueenNet achieves an order-of-magnitude reduction in model parameters while surpassing the classification performance of state-of-the-art methods.
Abstract Quantum-classical hybrid neural networks have recently emerged as a prominent research direction, combining the expressive power of quantum computing with the robustness and scalability of classical deep learning. These models have demonstrated significant potential, especially in image classification scenarios. However, existing hybrid architectures often fail to jointly model spatial and channel-wise features, which may constrain their representational capacity. In this work, we propose a novel quantum-enhanced convolutional neural network architecture that integrates Quantum Positional Encoding (QPE) and Quantum Channel Attention (QCA) mechanisms. These components respectively enhance spatial and channel-wise feature representations, while ensuring compatibility with conventional training pipelines. Experiments on the MNIST and Fashion-MNIST datasets demonstrate that the proposed model consistently outperforms classical CNN baselines in classification accuracy. Furthermore, experiments on the challenging CIFAR-10 dataset further validate the competitive performance of the proposed model, highlighting its strong generalization capability. These findings underscore the practical value of integrating quantum mechanisms into deep learning and emphasize their potential to advance intelligent visual recognition systems.
Medical image classification is a critical component of modern healthcare; however, accurate diagnosis remains challenging due to limited annotated datasets, class imbalance, and the high dimensionality of medical imaging data. To address these challenges, a hybrid quantum-classical neural network (HQCNN) is proposed, integrating classical deep learning with variational quantum learning for medical image classification. The proposed architecture combines a five-layer convolutional neural network (CNN) for hierarchical feature extraction with a lightweight 4-qubit variational quantum circuit (VQC) incorporating quantum state encoding, superposition and entanglement mechanisms, and a quantum attention-Fourier (QAF) module. This hybrid design aims to improve nonlinear feature representation and quantum parameter efficiency while maintaining a shallow quantum circuit suitable for noisy intermediate-scale quantum (NISQ)-era constraints. Experimental evaluation on six MedMNIST benchmark datasets demonstrated competitive performance across both binary and multi-class classification tasks. HQCNN achieved 98.88% accuracy on the binary subset of PathMNIST (classes 0 vs. 1), 97.61% accuracy on the multi-class OrganAMNIST dataset, and 86.29% accuracy on BreastMNIST. Comparative experiments and statistical analyses demonstrated consistent improvements over the controlled BHQNN baseline, while component-wise ablation studies showed that the QAF module, superposition and entanglement mechanisms, and expressive parameterized rotations contributed to classification performance in a complementary and dataset-dependent manner. Moreover, HQCNN reduced the number of trainable quantum parameters by approximately 55.6% compared with the baseline hybrid quantum neural network (BHQNN). Noise-aware simulations further showed that the model retained relatively stable predictive performance under moderate depolarizing noise, supporting further evaluation under near-term quantum computing conditions. Overall, the results demonstrate that HQCNN provides a parameter-efficient hybrid quantum-classical framework for medical image classification and offers a promising foundation for further investigation of quantum-enhanced medical image analysis.
Transformer now underpins modern AI as its core infrastructure. Its defining capability-dynamically focusing on the most relevant information in complex inputs-is bounded above by the self-attention scoring function. Quantum computing, with its superposition, entanglement, and probabilistic outputs, offers a fundamentally distinct computational framework for exploring beyond the design constraints of classical scoring functions. While quantum attention mechanisms have shown initial promise, existing works remain largely confined to redefining feature similarity measures, leaving the systematic use of parameterized quantum circuits (PQCs) as scoring functions largely unexplored; a substantial portion of existing schemes further rely on purely quantum architectures, precluding effective encoding of high-dimensional image inputs in the Noisy Intermediate-Scale Quantum era. We propose the Quantum Parameterized Self-Attention Network (QPSAN), implementing the self-attention scoring function via PQCs with only 5 trainable quantum parameters per layer. QPSAN computes query-key attention scores through quantum state encoding and joint measurement, yielding naturally bounded outputs without the explicit scaling of classical dot-product attention. We further establish a theoretical framework of the mathematical properties of this scoring function, demonstrating its potential to capture complex nonlinear query-key interactions, and quantifying the structural constraints of the encoding layer via effective degrees of freedom analysis. Experiments on four vision datasets show that QPSAN significantly outperforms the Vision Transformer (ViT) baseline, with the quantum representational advantage amplifying as data complexity increases. Ablation studies indicate that the performance gains may stem from the structural inductive bias of the quantum circuit rather than from parameter scale.
This paper presents an improved Quantum Convolutional Neural Network (QCNN) architecture that overcomes key limitations of current quantum-classical hybrid models for image classification. To address challenges in expressivity and feature extraction on noisy intermediate-scale quantum (NISQ) devices, we propose two key innovations: (1) Gate Encoding Optimization, which reduces quantum bit (qubit) usage while retaining spatial information, and (2) Quantum Channel Attention (QCA), a novel attention mechanism tailored for hybrid QCNNs which utilizes measurement-driven feedback to capture inter-channel dependencies. Evaluated on the MNIST dataset, our model achieves 95.68 % accuracy—on par with classical CNNs (95.73 %) and significantly better than a baseline QCNN (93.23%)—while reducing parameters by 49.6 %. These results demonstrate the proposed model's effectiveness and practicality for quantum machine learning in the NISQ era.
Recent advances in quantum computing have opened new pathways for enhancing deep learning architectures, particularly in domains characterized by high-dimensional and context-rich data such as natural language processing (NLP). In this work, we present a hybrid classical-quantum Transformer model that integrates a quantum-enhanced attention mechanism into the standard classical architecture. By embedding token representations into a quantum Hilbert space via parameterized variational circuits and exploiting entanglement-aware kernel similarities, the model captures complex semantic relationships beyond the reach of conventional dot-product attention. We demonstrate the effectiveness of this approach across diverse NLP benchmarks, showing improvements in both efficiency and representational capacity. The results section reveal that the quantum attention layer yields globally coherent attention maps and more separable latent features, while requiring comparatively fewer parameters than classical counterparts. These findings highlight the potential of quantum-classical hybrid models to serve as a powerful and resource-efficient alternative to existing attention mechanisms in NLP.