Saved in:
Bibliographic Details
Main Authors: Wang, Mingzhu, Shang, Yun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.12291
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915553601388544
author Wang, Mingzhu
Shang, Yun
author_facet Wang, Mingzhu
Shang, Yun
contents Quantum machine learning (QML) holds promise for computational advantage, yet progress on real-world tasks is hindered by classical preprocessing and noisy devices. We introduce ViT-QCNN-FT, a hybrid framework that integrates a fine-tuned Vision Transformer with a quantum convolutional neural network (QCNN) to compress high-dimensional images into features suited for noisy intermediate-scale quantum (NISQ) devices. By systematically probing entanglement, we show that ansatzes with uniformly distributed entanglement entropy consistently deliver superior non-local feature fusion and state-of-the-art accuracy (99.77% on CIFAR-10). Surprisingly, quantum noise emerges as a double-edged factor: in some cases, it enhances accuracy (+2.71% under amplitude damping). Strikingly, substituting the QCNN with classical counterparts of equal parameter count leads to a dramatic 29.36% drop, providing unambiguous evidence of quantum advantage. Our study establishes a principled pathway for co-designing classical and quantum architectures, pointing toward practical QML capable of tackling complex, high-dimensional learning tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12291
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hybrid Vision Transformer and Quantum Convolutional Neural Network for Image Classification
Wang, Mingzhu
Shang, Yun
Quantum Physics
Quantum machine learning (QML) holds promise for computational advantage, yet progress on real-world tasks is hindered by classical preprocessing and noisy devices. We introduce ViT-QCNN-FT, a hybrid framework that integrates a fine-tuned Vision Transformer with a quantum convolutional neural network (QCNN) to compress high-dimensional images into features suited for noisy intermediate-scale quantum (NISQ) devices. By systematically probing entanglement, we show that ansatzes with uniformly distributed entanglement entropy consistently deliver superior non-local feature fusion and state-of-the-art accuracy (99.77% on CIFAR-10). Surprisingly, quantum noise emerges as a double-edged factor: in some cases, it enhances accuracy (+2.71% under amplitude damping). Strikingly, substituting the QCNN with classical counterparts of equal parameter count leads to a dramatic 29.36% drop, providing unambiguous evidence of quantum advantage. Our study establishes a principled pathway for co-designing classical and quantum architectures, pointing toward practical QML capable of tackling complex, high-dimensional learning tasks.
title Hybrid Vision Transformer and Quantum Convolutional Neural Network for Image Classification
topic Quantum Physics
url https://arxiv.org/abs/2510.12291