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

Chinese Journal of Physics

Superposition-enhanced quantum neural network for multi-class image classification

Qi Bai, Xianliang Hu

Published Mar 18, 2024• 18 citations
Publisher
DOI
10.1016/j.cjph.2024.03.026

Related papers

Hybrid quantum convolutional neural network for multi-channel image classification

Cai Zhang, Li Zheng, Haozhen Situ

Physica A Statistical Mechanics and its Applications•Nov 20, 2025•4 citations

Quantum convolutional neural networks for multiclass image classification

Shangshang Shi, Zhimin Wang, Jiaxin Li +4 more

Quantum Information Processing•May 13, 2024•15 citations

Three quantum neural network architectures for multiclass image classification

Guoxin Qu, Xianglong Yu, Zhimin Wang +1 more

Quantum neural networks (QNNs) integrate the advantages of quantum information with the formidable capabilities of classical neural networks, exhibiting notable potential in image classification tasks. However, the performance of current QNNs in processing multi-class image classification tasks still leaves room for improvement. In this paper, we propose three QNN architectures to enhance the accuracy of multi-class image classification by utilizing techniques of overparameterization, dense pooling, and local feature extraction. These networks are capable of mapping conventional data to the amplitudes of quantum states via amplitude encoding, eschewing the need for traditional dimensionality reduction techniques. Following processing with parameterized quantum circuits (PQCs), we conduct quantum measurements to extract feature information. We validate the proposed architectures using the MNIST dataset for eight-class image classification problems. The experimental results unequivocally demonstrate that the three techniques we employed significantly enhance the accuracy of QNNs in multi-class image classification tasks.

International Conference on Algorithms, Network, and Communication Technology (ICANCT)•Mar 3, 2025•2 citations

Optimization Techniques of Quantum Neural Network for Image Classification

Prateek Karkera, R Srivaramangai

Lecture notes in networks and systems•Jan 1, 2024•0 citations

Hybrid quantum neural network structures for image multi-classification

Mingrui Shi, Haozhen Situ, Cai Zhang

Abstract Image classification is a fundamental problem in computer vision, and neural networks provide an effective solution. With the advancement of quantum technology, quantum neural networks have attracted a lot of attention. However, they are only suitable for low-dimensional data and require dimensionality reduction and quantum encoding. Two image classification methods have recently emerged: one employs PCA for dimensionality reduction and angular encoding, and the other integrates QNN into a CNN to improve performance. Despite numerous algorithms, the differences between them remain unclear. This study explores these algorithms’ performance in multi-class image classification and proposes an optimized hybrid quantum neural network suitable for the current environment. As the number of classes increases, research on PCA-based quantum algorithms reveals the barren plateau problem of QNN, which is not suitable for multiple classes in a hybrid setting. Our proposed model combining traditional CNN with QNN addresses QNN’s multi-class training difficulties to some extent and achieves satisfactory classification results. Nevertheless, its accuracy remains below that of the top-performing CNN models. Furthermore, we investigate transfer learning in hybrid quantum neural network models and assess the performance of our models on the quantum hardware from IBM. In conclusion, quantum neural networks show promise but require further research and optimization, facing challenges ahead.

arXiv:2308.16005•Physica Scripta•Apr 12, 2024•32 citations

Design of Superior Parameterized Quantum Circuits for Quantum Image Classification

Shraddha Mishra, Chi‐Yi Tsai

In this paper, we present a novel quantum neural network (QNN) algorithm enhanced with transfer learning to perform multi-class image classification. The proposed QNN extracts quantum image encoding measurements through the quantum state tomography framework and passes the sampled features through the classical neural network architecture to the proposed learnable parameterized quantum circuit (PQC) followed by gradient update via quantum backpropagation. We benchmark three different PQCs to demonstrate that our proposed algorithm outperforms similar classical CNN architecture in test accuracy on CIFAR10 and MNIST datasets. Present results more prominently establish the success of PQC designs which will be further used in the design of 2D quantum convolutional neural network (QCNN).

International Conference on Computer and Automation Engineering•Mar 25, 2022•6 citations
Quantum neural networks (QNNs) integrate the advantages of quantum information with the formidable capabilities of classical neural networks, exhibiting notable potential in image classification tasks. However, the performance of current QNNs in processing multi-class image classification tasks still leaves room for improvement. In this paper, we propose three QNN architectures to enhance the accuracy of multi-class image classification by utilizing techniques of overparameterization, dense pooling, and local feature extraction. These networks are capable of mapping conventional data to the amplitudes of quantum states via amplitude encoding, eschewing the need for traditional dimensionality reduction techniques. Following processing with parameterized quantum circuits (PQCs), we conduct quantum measurements to extract feature information. We validate the proposed architectures using the MNIST dataset for eight-class image classification problems. The experimental results unequivocally demonstrate that the three techniques we employed significantly enhance the accuracy of QNNs in multi-class image classification tasks.
Abstract Image classification is a fundamental problem in computer vision, and neural networks provide an effective solution. With the advancement of quantum technology, quantum neural networks have attracted a lot of attention. However, they are only suitable for low-dimensional data and require dimensionality reduction and quantum encoding. Two image classification methods have recently emerged: one employs PCA for dimensionality reduction and angular encoding, and the other integrates QNN into a CNN to improve performance. Despite numerous algorithms, the differences between them remain unclear. This study explores these algorithms’ performance in multi-class image classification and proposes an optimized hybrid quantum neural network suitable for the current environment. As the number of classes increases, research on PCA-based quantum algorithms reveals the barren plateau problem of QNN, which is not suitable for multiple classes in a hybrid setting. Our proposed model combining traditional CNN with QNN addresses QNN’s multi-class training difficulties to some extent and achieves satisfactory classification results. Nevertheless, its accuracy remains below that of the top-performing CNN models. Furthermore, we investigate transfer learning in hybrid quantum neural network models and assess the performance of our models on the quantum hardware from IBM. In conclusion, quantum neural networks show promise but require further research and optimization, facing challenges ahead.
In this paper, we present a novel quantum neural network (QNN) algorithm enhanced with transfer learning to perform multi-class image classification. The proposed QNN extracts quantum image encoding measurements through the quantum state tomography framework and passes the sampled features through the classical neural network architecture to the proposed learnable parameterized quantum circuit (PQC) followed by gradient update via quantum backpropagation. We benchmark three different PQCs to demonstrate that our proposed algorithm outperforms similar classical CNN architecture in test accuracy on CIFAR10 and MNIST datasets. Present results more prominently establish the success of PQC designs which will be further used in the design of 2D quantum convolutional neural network (QCNN).