Selective Feature Re-Encoded Quantum Convolutional Neural Network with Joint Optimization for Image Classification

2025-07-02

AI Summary

To address the limited image feature representation capability in quantum convolutional neural networks (QCNNs), this paper proposes a selective quantum feature recoding mechanism and a parallel dual-path QCNN architecture. Methodologically, it fuses complementary low-dimensional features extracted via PCA and classical autoencoders, then applies learnable quantum gates to selectively recode salient features; a parallel QCNN structure enables dual-path quantum feature fusion and end-to-end joint parameter optimization. The key contributions are: (i) the first integration of selective quantum feature recoding into QCNNs, and (ii) the design of a parallel quantum architecture supporting unified optimization. Evaluated on MNIST and Fashion-MNIST binary classification tasks, the proposed model achieves significantly higher accuracy than standalone QCNNs, classical ensemble methods, and decision-level fusion baselines—demonstrating enhanced representational capacity and generalization performance.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Quantum Machine Learning (QML) has seen significant advancements, driven by recent improvements in Noisy Intermediate-Scale Quantum (NISQ) devices. Leveraging quantum principles such as entanglement and superposition, quantum convolutional neural networks (QCNNs) have demonstrated promising results in classifying both quantum and classical data. This study examines QCNNs in the context of image classification and proposes a novel strategy to enhance feature processing and a QCNN architecture for improved classification accuracy. First, a selective feature re-encoding strategy is proposed, which directs the quantum circuits to prioritize the most informative features, thereby effectively navigating the crucial regions of the Hilbert space to find the optimal solution space. Secondly, a novel parallel-mode QCNN architecture is designed to simultaneously incorporate features extracted by two classical methods, Principal Component Analysis (PCA) and Autoencoders, within a unified training scheme. The joint optimization involved in the training process allows the QCNN to benefit from complementary feature representations, enabling better mutual readjustment of model parameters. To assess these methodologies, comprehensive experiments have been performed using the widely used MNIST and Fashion MNIST datasets for binary classification tasks. Experimental findings reveal that the selective feature re-encoding method significantly improves the quantum circuit's feature processing capability and performance. Furthermore, the jointly optimized parallel QCNN architecture consistently outperforms the individual QCNN models and the traditional ensemble approach involving independent learning followed by decision fusion, confirming its superior accuracy and generalization capabilities.

Problem

• Enhance QCNN feature processing for image classification
• Optimize quantum circuits for informative feature prioritization
• Improve classification accuracy with parallel-mode QCNN architecture

Innovation

• Selective feature re-encoding prioritizes informative features
• Parallel-mode QCNN combines PCA and Autoencoder features
• Joint optimization enhances complementary feature representations