将量子电路融入RWKV模型，提升图像分类的特征表达能力。
Vision-QRWKV: Exploring Quantum-Enhanced RWKV Models for Image Classification
- 用变分量子电路增强RWKV的通道混合模块，实现非线性变换。
- 在14个数据集上测试，量子版在9个含噪声或细微差异的数据集上表现更优。
- 首次将量子增强RWKV用于视觉任务，适合研究轻量级量子神经网络者。
近年来，量子机器学习在提升经典神经网络架构方面展现出潜力，尤其适用于处理复杂高维数据。本文基于时序建模的前期工作，首次将受激量子电路（VQC）引入重获加权键值（RWKV）架构，提出Vision-QRWKV，用于图像分类任务。通过在RWKV的通道混合部分嵌入变分量子电路，模型旨在增强非线性特征变换能力与视觉表征的表达力。我们在包含MedMNIST、MNIST、FashionMNIST等在内的14个医学及标准图像分类基准上评估了经典与量子增强版本的RWKV模型。结果表明，量子增强模型在多数数据集上优于经典版本，尤其在类别间差异细微或存在噪声的数据集（如ChestMNIST、RetinaMNIST、BloodMNIST）中表现突出。本研究首次系统地将量子增强型RWKV应用于视觉领域，为轻量级高效视觉任务中的量子模型架构提供了洞见与未来方向。
原文摘要 · Abstract (English)
Recent advancements in quantum machine learning have shown promise in enhancing classical neural network architectures, particularly in domains involving complex, high-dimensional data. Building upon prior work in temporal sequence modeling, this paper introduces Vision-QRWKV, a hybrid quantum-classical extension of the Receptance Weighted Key Value (RWKV) architecture, applied for the first time to image classification tasks. By integrating a variational quantum circuit (VQC) into the channel mixing component of RWKV, our model aims to improve nonlinear feature transformation and enhance the expressive capacity of visual representations. We evaluate both classical and quantum RWKV models on a diverse collection of 14 medical and standard image classification benchmarks, including MedMNIST datasets, MNIST, and FashionMNIST. Our results demonstrate that the quantum-enhanced model outperforms its classical counterpart on a majority of datasets, particularly those with subtle or noisy class distinctions (e.g., ChestMNIST, RetinaMNIST, BloodMNIST). This study represents the first systematic application of quantum-enhanced RWKV in the visual domain, offering insights into the architectural trade-offs and future potential of quantum models for lightweight and efficient vision tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。