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

2025-01-22

AI Summary

To address the high computational overhead of processing high-dimensional features in quantum convolutional neural networks (QCNNs) and the limited representational capacity of quantum-classical hybrid models for image segmentation, this paper proposes QuFeX—the first differentiable quantum feature extraction module designed specifically for deep learning bottleneck layers. QuFeX enables efficient quantum feature compression in low-dimensional latent spaces, significantly reducing the number of parallel quantum circuit evaluations required. Integrated into the U-Net backbone, it forms Qu-Net: an end-to-end trainable architecture supporting joint quantum-classical gradient optimization and hybrid forward/backward propagation. Experiments on medical image segmentation demonstrate that Qu-Net consistently outperforms the standard U-Net baseline, achieving simultaneous improvements in both segmentation accuracy and inference efficiency. This work provides the first empirical validation of substantial performance gains from differentiable quantum feature extraction in segmentation tasks.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Segmentation
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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.

Problem

• Low-dimensional feature extraction
• Quantum Convolutional Neural Networks
• Hybrid Quantum-Classical Deep Learning

Innovation

• Quantum Feature Extraction
• Quantum-Classic Hybrid Models
• Image Segmentation