Quantum autoencoders for image classification

2025-02-21

AI Summary

Classical machine learning methods face inherent limitations in processing high-dimensional image data, while existing quantum approaches—such as quantum convolutional neural networks (QCNNs)—rely on classical optimization and auxiliary qubits, undermining full quantum coherence. Method: This paper proposes an end-to-end purely quantum image classification framework based on a quantum autoencoder (QAE), performing quantum-state encoding, unsupervised pretraining, and supervised fine-tuning entirely within parameterized quantum circuits (PQCs), without classical intermediate computation or ancillary qubits. Contribution/Results: To our knowledge, this is the first work to directly apply QAEs to multi-class image classification. We systematically analyze how ansatz topology affects classification performance. On a four-class image benchmark, our method achieves accuracy comparable to classical baselines while reducing trainable parameters by over 60%. These results demonstrate the feasibility and efficiency of a low-parameter, fully quantum learning paradigm.

Technology Category

Machine Learning: Quantum Machine LearningComputer Vision: Learning & Optimization for CVSearch and Optimization: Learning to Search

Application Category

Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingSecurity and Privacy: Security and privacy of machine learning and AI applicationsEconomics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Classical machine learning often struggles with complex, high-dimensional data. Quantum machine learning offers a potential solution, promising more efficient processing. While the quantum convolutional neural network (QCNN), a hybrid quantum-classical algorithm, is suitable for current noisy intermediate-scale quantum-era hardware, its learning process relies heavily on classical computation. Future large-scale, gate-based quantum computers could unlock the full potential of quantum effects in machine learning. In contrast to QCNNs, quantum autoencoders (QAEs) leverage classical optimization solely for parameter tuning. Data compression and reconstruction are handled entirely within quantum circuits, enabling purely quantum-based feature extraction. This study introduces a novel image-classification approach using QAEs, achieving classification without requiring additional qubits compared with conventional QAE implementations. The quantum circuit structure significantly impacts classification accuracy. Unlike hybrid methods such as QCNN, QAE-based classification emphasizes quantum computation. Our experiments demonstrate high accuracy in a four-class classification task, evaluating various quantum-gate configurations to understand the impact of different parameterized quantum circuit (ansatz) structures on classification performance. Our results reveal that specific ansatz structures achieve superior accuracy, and we provide an analysis of their effectiveness. Moreover, the proposed approach achieves performance comparable to that of conventional machine-learning methods while significantly reducing the number of parameters requiring optimization. These findings indicate that QAEs can serve as efficient classification models with fewer parameters and highlight the potential of utilizing quantum circuits for complete end-to-end learning, a departure from hybrid approaches such as QCNN.

Problem

• Quantum autoencoders for image classification
• Efficient processing of high-dimensional data
• Pure quantum-based feature extraction

Innovation

• Quantum autoencoders for feature extraction
• Pure quantum-based image classification
• Reduced parameters for efficient learning