Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2507.11217 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913942671982592 |
|---|---|
| author | Hsu, Yu-Chao Chen, Kuan-Cheng Li, Tai-Yue Chen, Nan-Yow |
| author_facet | Hsu, Yu-Chao Chen, Kuan-Cheng Li, Tai-Yue Chen, Nan-Yow |
| contents | In this work, we introduce the Quantum Adaptive Excitation Network (QAE-Net), a hybrid quantum-classical framework designed to enhance channel attention mechanisms in Convolutional Neural Networks (CNNs). QAE-Net replaces the classical excitation block of Squeeze-and-Excitation modules with a shallow Variational Quantum Circuit (VQC), leveraging quantum superposition and entanglement to capture higher-order inter-channel dependencies that are challenging to model with purely classical approaches. We evaluate QAE-Net on benchmark image classification tasks, including MNIST, FashionMNIST, and CIFAR-10, and observe consistent performance improvements across all datasets, with particularly notable gains on tasks involving three-channel inputs. Furthermore, experimental results demonstrate that increasing the number of variational layers in the quantum circuit leads to progressively higher classification accuracy, underscoring the expressivity benefits of deeper quantum models. These findings highlight the potential of integrating VQCs into CNN architectures to improve representational capacity while maintaining compatibility with near-term quantum devices. The proposed approach is tailored for the Noisy Intermediate-Scale Quantum (NISQ) era, offering a scalable and feasible pathway for deploying quantum-enhanced attention mechanisms in practical deep learning workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_11217 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quantum Adaptive Excitation Network with Variational Quantum Circuits for Channel Attention Hsu, Yu-Chao Chen, Kuan-Cheng Li, Tai-Yue Chen, Nan-Yow Quantum Physics In this work, we introduce the Quantum Adaptive Excitation Network (QAE-Net), a hybrid quantum-classical framework designed to enhance channel attention mechanisms in Convolutional Neural Networks (CNNs). QAE-Net replaces the classical excitation block of Squeeze-and-Excitation modules with a shallow Variational Quantum Circuit (VQC), leveraging quantum superposition and entanglement to capture higher-order inter-channel dependencies that are challenging to model with purely classical approaches. We evaluate QAE-Net on benchmark image classification tasks, including MNIST, FashionMNIST, and CIFAR-10, and observe consistent performance improvements across all datasets, with particularly notable gains on tasks involving three-channel inputs. Furthermore, experimental results demonstrate that increasing the number of variational layers in the quantum circuit leads to progressively higher classification accuracy, underscoring the expressivity benefits of deeper quantum models. These findings highlight the potential of integrating VQCs into CNN architectures to improve representational capacity while maintaining compatibility with near-term quantum devices. The proposed approach is tailored for the Noisy Intermediate-Scale Quantum (NISQ) era, offering a scalable and feasible pathway for deploying quantum-enhanced attention mechanisms in practical deep learning workflows. |
| title | Quantum Adaptive Excitation Network with Variational Quantum Circuits for Channel Attention |
| topic | Quantum Physics |
| url | https://arxiv.org/abs/2507.11217 |