QuFeX: Quantum feature extraction module for hybrid quantum-classical deep neural networks

TL;DR

This paper introduces QuFeX, a quantum feature extraction module that enhances hybrid quantum-classical neural networks by reducing complexity and improving performance in image segmentation tasks.

Contribution

The paper presents QuFeX, a novel quantum module for feature extraction that integrates seamlessly into deep neural networks, enabling more efficient hybrid quantum-classical architectures.

Findings

Qu-Net outperforms baseline U-Net in segmentation accuracy.

QuFeX reduces the number of evaluations needed in quantum neural networks.

Hybrid models with QuFeX show promising potential for real-world applications.

Abstract

We introduce Quantum Feature Extraction (QuFeX), a novel quantum machine learning module. The proposed module enables feature extraction in a reduced-dimensional space, significantly decreasing the number of parallel evaluations required in typical quantum convolutional neural network architectures. Its design allows seamless integration into deep classical neural networks, making it particularly suitable for hybrid quantum-classical models. As an application of QuFeX, we propose Qu-Net -- a hybrid architecture which integrates QuFeX at the bottleneck of a U-Net architecture. The latter is widely used for image segmentation tasks such as medical imaging and autonomous driving. Our numerical analysis indicates that the Qu-Net can achieve superior segmentation performance compared to a U-Net baseline. These results highlight the potential of QuFeX to enhance deep neural networks by leveraging hybrid computational paradigms, providing a path towards a robust framework for real-world applications requiring precise feature extraction.