Vision-QRWKV: Exploring Quantum-Enhanced RWKV Models for Image Classification

TL;DR

This paper introduces Vision-QRWKV, a hybrid quantum-classical model that enhances image classification by integrating quantum circuits into the RWKV architecture, showing improved performance on various benchmarks.

Contribution

It is the first to apply quantum-enhanced RWKV to visual tasks, demonstrating improved accuracy on multiple image classification datasets.

Findings

Quantum RWKV outperforms classical RWKV on most datasets.

Quantum models excel in subtle or noisy class distinctions.

First systematic application of quantum RWKV in vision domain.

Abstract

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.