Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2208.14708 · Neurocomputing

Classical-to-quantum convolutional neural network transfer learning

Juhyeon Kim, Joonsuk Huh, Daniel K. Park

Published Jul 29, 2023• 68 citations
arXivHTMLPDF
DOI
10.1016/j.neucom.2023.126643

Related papers

Classification of knee osteoarthritis based on quantum-to-classical transfer learning

Yumin Dong, Xuanxuan Che, Yanying Fu +3 more

Quantum machine learning takes advantage of features such as quantum computing superposition and entanglement to enable better performance of machine learning models. In this paper, we first propose an improved hybrid quantum convolutional neural network (HQCNN) model. The HQCNN model was used to pre-train brain tumor dataset (MRI) images. Next, the quantum classical transfer learning (QCTL) approach is used to fine-tune and extract features based on pre-trained weights. A hybrid quantum convolutional network structure was used to test the osteoarthritis of the knee dataset (OAI) and to quantitatively evaluate standard metrics to verify the robustness of the classifier. The final experimental results show that the QCTL method can effectively classify knee osteoarthritis with a classification accuracy of 98.36%. The quantum-to-classical transfer learning method improves classification accuracy by 1.08%. How to use different coding techniques in HQCNN models applied to medical image analysis is also a future research direction.

Frontiers in Physics•Jul 17, 2023•13 citations

Hybrid quantum-classical convolutional neural networks

Junhua Liu, Kwan Hui Lim, Kristin Lee Wood +3 more

arXiv:1911.02998•Science China Physics Mechanics and Astronomy•Aug 4, 2021•291 citations

Quantum convolutional neural networks

Iris Cong, Soonwon Choi, Mikhail D. Lukin

arXiv:1810.03787•Nature Physics•Aug 26, 2019•1,523 citations

Quantum‐inspired Arecanut X‐ray image classification using transfer learning

Praveen M Naik, Bhawana Rudra

Abstract Arecanut X‐ray images accurately represent their internal structure. A comparative analysis of transfer learning‐based classification, employing both a traditional convolutional neural network (CNN) and an advanced quantum convolutional neural network (QCNN) approach is conducted. The investigation explores various transfer learning models with different sizes to identify the most suitable one for achieving enhanced accuracy. The Shufflenet model with a scale factor of 2.0 attains the highest classification accuracy of 97.72% using the QCNN approach, with a model size of 28.40 MB. Out of the 12 transfer learning models tested, 9 exhibit improved classification accuracy when using QCNN models compared to the traditional CNN‐based transfer learning approach. Consequently, the exploration of CNN and QCNN‐based classification reveals that QCNN outperforms traditional CNN models in accuracy within the transfer learning framework. Further experiments with qubits suggest that utilising 4 qubits is optimal for classification operations in this context.

IET Quantum Communication•Jun 6, 2024•2 citations

Quantum convolutional neural network for classical data classification

Tak Hur, Leeseok Kim, Daniel K. Park

arXiv:2108.00661•Quantum Machine Intelligence•Feb 10, 2022•384 citations

Adversarial Robustness of Hybrid Quantum Convolutional Neural Networks in Medical Image Analysis

Τheofanis Kalampokas, Εleni Vrochidou, George A. Papakostas

In this work, we investigate the performance of hybrid quantum-classical convolutional neural networks (QCNNs) in medical image classification under the presence of adversarial attacks. Adversarial attacks pose a significant threat to image classification models, since they introduce subtle perturbations to input images, leading to incorrect predictions. Specifically, in this work, 10 QCNNs with their corresponding classic Convolutional Neural Networks (CNNs) counterparts are comparatively examined for their robustness, on two different medical image datasets using transfer learning, under two different adversarial attacks. In a subsequent step, the implementation of training models from scratch is also evaluated. With transfer learning on the X-ray dataset, CNN and QCNN models achieve high and comparable performance across most backbones. On the histopathological dataset, CNNs and QCNNs often generalize worse compared to the X-ray dataset, indicating head overfitting under domain shift. The adversarial evaluation results highlight that most models' robustness comes from the backbone rather than the head. QCNN models perform comparably to CNNs under attack and show improvements when trained from scratch. Overall, the results indicate that integrating quantum circuit mechanisms into classical CNN architectures can enhance the robustness of models in medical imaging tasks, representing a promising domain that warrants further investigation.

CRC Press eBooks•Sep 10, 2026•0 citations
Quantum machine learning takes advantage of features such as quantum computing superposition and entanglement to enable better performance of machine learning models. In this paper, we first propose an improved hybrid quantum convolutional neural network (HQCNN) model. The HQCNN model was used to pre-train brain tumor dataset (MRI) images. Next, the quantum classical transfer learning (QCTL) approach is used to fine-tune and extract features based on pre-trained weights. A hybrid quantum convolutional network structure was used to test the osteoarthritis of the knee dataset (OAI) and to quantitatively evaluate standard metrics to verify the robustness of the classifier. The final experimental results show that the QCTL method can effectively classify knee osteoarthritis with a classification accuracy of 98.36%. The quantum-to-classical transfer learning method improves classification accuracy by 1.08%. How to use different coding techniques in HQCNN models applied to medical image analysis is also a future research direction.
Abstract Arecanut X‐ray images accurately represent their internal structure. A comparative analysis of transfer learning‐based classification, employing both a traditional convolutional neural network (CNN) and an advanced quantum convolutional neural network (QCNN) approach is conducted. The investigation explores various transfer learning models with different sizes to identify the most suitable one for achieving enhanced accuracy. The Shufflenet model with a scale factor of 2.0 attains the highest classification accuracy of 97.72% using the QCNN approach, with a model size of 28.40 MB. Out of the 12 transfer learning models tested, 9 exhibit improved classification accuracy when using QCNN models compared to the traditional CNN‐based transfer learning approach. Consequently, the exploration of CNN and QCNN‐based classification reveals that QCNN outperforms traditional CNN models in accuracy within the transfer learning framework. Further experiments with qubits suggest that utilising 4 qubits is optimal for classification operations in this context.
In this work, we investigate the performance of hybrid quantum-classical convolutional neural networks (QCNNs) in medical image classification under the presence of adversarial attacks. Adversarial attacks pose a significant threat to image classification models, since they introduce subtle perturbations to input images, leading to incorrect predictions. Specifically, in this work, 10 QCNNs with their corresponding classic Convolutional Neural Networks (CNNs) counterparts are comparatively examined for their robustness, on two different medical image datasets using transfer learning, under two different adversarial attacks. In a subsequent step, the implementation of training models from scratch is also evaluated. With transfer learning on the X-ray dataset, CNN and QCNN models achieve high and comparable performance across most backbones. On the histopathological dataset, CNNs and QCNNs often generalize worse compared to the X-ray dataset, indicating head overfitting under domain shift. The adversarial evaluation results highlight that most models' robustness comes from the backbone rather than the head. QCNN models perform comparably to CNNs under attack and show improvements when trained from scratch. Overall, the results indicate that integrating quantum circuit mechanisms into classical CNN architectures can enhance the robustness of models in medical imaging tasks, representing a promising domain that warrants further investigation.