Quantum Adaptive Excitation Network with Variational Quantum Circuits for Channel Attention

TL;DR

This paper proposes a hybrid quantum-classical neural network framework that uses variational quantum circuits to improve channel attention in CNNs, demonstrating enhanced performance on image classification benchmarks.

Contribution

It introduces QAE-Net, replacing classical excitation blocks with shallow VQCs, leveraging quantum properties to model complex channel dependencies in CNNs.

Findings

QAE-Net outperforms classical models on MNIST, FashionMNIST, and CIFAR-10.

Deeper variational quantum circuits yield higher classification accuracy.

The approach is suitable for near-term quantum devices in practical deep learning applications.

Abstract

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.