混合量子-经典神经网络中的特征自适应融合用于鲁棒的生物医学图像分类
Feature-Adaptive Fusion in Hybrid Quantum-Classical Neural Networks for Robust Biomedical Image Classification
浏览论文内容
中文总结 AI 辅助
提出特征自适应融合混合量子-经典神经网络（FAF-HQNN），通过动态加权经典与量子预测，在MedMNIST基准上提升生物医学图像分类的准确性与鲁棒性。
中文摘要 AI 辅助
混合量子-经典神经网络为在含噪声中等规模量子（NISQ）时代将量子电路融入机器学习提供了一种有前景的方法。然而，现有的混合模型通常依赖固定或全局共享的融合策略，这可能限制其利用量子分支所携带的互补信息的能力，尤其是在分布偏移的情况下。在本工作中，我们提出了一种用于生物医学图像分类的特征自适应融合混合量子-经典神经网络（FAF-HQNN）。该模型将经典深度特征编码器与变分量子电路（VQC）相结合，并引入特征自适应融合机制，以动态加权经典和量子预测。我们在两个MedMNIST基准数据集（PathMNIST和BloodMNIST）上，在干净和损坏的测试条件下评估了FAF-HQNN。FAF-HQNN在干净数据上取得了所比较方法中最强的整体性能，并在高斯、椒盐和泊松损坏下展现出更高的鲁棒性。对电路布局、测量基和深度的进一步分析表明，即使是浅层变分量子电路也能提供有用的互补信息。这些结果表明，特征自适应融合是提高生物医学图像分类中混合量子-经典模型准确性和鲁棒性的有效策略。
英文摘要
Hybrid quantum-classical neural networks provide a promising approach for incorporating quantum circuits into machine learning in the noisy intermediate-scale quantum regime. However, existing hybrid models often rely on fixed or globally shared fusion strategies, which may limit their ability to exploit complementary information carried by quantum branches, especially under distribution shifts. In this work, we propose a Feature-Adaptive Fusion Hybrid Quantum-Classical Neural Network (FAF-HQNN) for biomedical image classification. The model combines a classical deep feature encoder with a variational quantum circuit (VQC) and introduces a feature-adaptive fusion mechanism to dynamically weight classical and quantum predictions. We evaluate FAF-HQNN on two MedMNIST benchmarks, PathMNIST and BloodMNIST, under clean and corrupted test conditions. FAF-HQNN achieves the strongest overall performance on clean data among the compared methods and shows improved robustness under Gaussian, salt-and-pepper, and Poisson corruptions. Further analysis of circuit layout, measurement basis, and depth shows that even shallow variational quantum circuits can provide useful complementary information. These results demonstrate that feature-adaptive fusion is an effective strategy for improving accuracy and robustness in hybrid quantum-classical models for biomedical image classification.
发表机构
- College of Information Science and Engineering, Zaozhuang University（枣庄学院信息科学与工程学院）
- School of Cyberspace Security, Beijing University of Posts and Telecommunications（北京邮电大学网络空间安全学院）
- Hangzhou City University（杭州城市学院）
- School of Artificial Intelligence, Henan University（河南大学人工智能学院）
- China Information Technology Security Evaluation Center（中国信息安全测评中心）
- Network Center, Zaozhuang University（枣庄学院网络中心）
机构由 AI 辅助整理，请以论文原文为准。
