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

Knowledge-Based Systems

Quantum Fourier Transform Neural Network with image blockwise representation for image classification

Desheng Kong, Kangning An, Kairan Zhang, Mingyang Yu, Yulong Fu, Wei Wang, Jing Xu, Donglin Wang

Published Apr 11, 2026• 0 citations
Publisher
DOI
10.1016/j.knosys.2026.115937

Related papers

Comparing Concepts of Quantum and Classical Neural Network Models for Image Classification Task

Rafał Potempa, Sebastian Porębski

arXiv:2108.08875•Lecture notes in networks and systems•Aug 17, 2021•21 citations

QFCNN: A Dual-Branch Hybrid Quantum–Classical Convolutional Neural Network Based on the Quantum Fourier Transform for Image Classification

Zhen Zhang, Chenhao Huang, Hongyang Ma +2 more

Image classification is a fundamental task in computer vision. Although classical convolutional neural networks are particularly effective at extracting local spatial features, they are inherently limited in their ability to capture global frequency-domain information. To address this limitation, this paper introduces a hybrid model that couples a classical convolutional feature extraction branch with a quantum feature extraction branch built upon the quantum Fourier transform. The quantum branch maps the input into a low-dimensional representation and processes it through a sequence of quantum encoding, the quantum Fourier transform, a variational quantum circuit, and the inverse quantum Fourier transform; the resulting quantum features are concatenated with the classical features and jointly used for the final classification. Ablation studies quantify the individual contribution of each quantum component, and systematic experiments on the MNIST, Fashion-MNIST, and CIFAR-10 benchmark datasets, conducted over multiple independent random seeds on a strictly held-out test set, show that the complete architecture consistently outperforms its purely classical counterparts. All results and comparative analyses are presented in the experimental section.

Computation•Nov 10, 2026•0 citations

Quantum convolutional neural network for image classification

Guoming Chen, Qiang Chen, Shun Long +3 more

Pattern Analysis and Applications•Sep 24, 2022•132 citations

Quantum image representation-based quantum neural networks for binary classification

Abhishek Tiwari, Shivanshu Siyanwal, Saiyam Sakhuja +2 more

Abstract We propose a comparative analysis of quantum image classification utilising a circularly-entangled quantum neural network (QNN) in conjunction with four quantum image representation (QIR) strategies: Novel Amplitude Square Sum (NASS), Quantum Block Image Representation (QBIR), Fourier-based Threshold Quantum Representation (FTQR), and Flexible Representation for Quantum Color Image (FRQCI). A methodical assessment of accuracy, loss convergence, and quantum resource requirements was made possible by the encoding of binary MNIST digits (0 and 1) at image sizes of \((2\times2)\), \((4\times4)\), and \((8\times8)\). Our findings demonstrate that, whereas QBIR-QNN offers competitive results with shallow circuits at the expense of greater qubit counts, NASS-QNN continuously converges to high training accuracy with stable parameters, achieving the most reliable and accurate performance. On the other hand, the instability and large resource overheads of FTQR-QNN and FRQCI-QNN restrict their applicability in the NISQ regime. The most promising approaches are highlighted by these results: NASS and QBIR, which provide workable trade-offs between hardware implementability, accuracy, and convergence stability.

The Journal of Supercomputing•Jun 11, 2026•0 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

Quantum convolutional neural networks for multiclass image classification

Shangshang Shi, Zhimin Wang, Jiaxin Li +4 more

Quantum Information Processing•May 13, 2024•19 citations
Image classification is a fundamental task in computer vision. Although classical convolutional neural networks are particularly effective at extracting local spatial features, they are inherently limited in their ability to capture global frequency-domain information. To address this limitation, this paper introduces a hybrid model that couples a classical convolutional feature extraction branch with a quantum feature extraction branch built upon the quantum Fourier transform. The quantum branch maps the input into a low-dimensional representation and processes it through a sequence of quantum encoding, the quantum Fourier transform, a variational quantum circuit, and the inverse quantum Fourier transform; the resulting quantum features are concatenated with the classical features and jointly used for the final classification. Ablation studies quantify the individual contribution of each quantum component, and systematic experiments on the MNIST, Fashion-MNIST, and CIFAR-10 benchmark datasets, conducted over multiple independent random seeds on a strictly held-out test set, show that the complete architecture consistently outperforms its purely classical counterparts. All results and comparative analyses are presented in the experimental section.
Abstract We propose a comparative analysis of quantum image classification utilising a circularly-entangled quantum neural network (QNN) in conjunction with four quantum image representation (QIR) strategies: Novel Amplitude Square Sum (NASS), Quantum Block Image Representation (QBIR), Fourier-based Threshold Quantum Representation (FTQR), and Flexible Representation for Quantum Color Image (FRQCI). A methodical assessment of accuracy, loss convergence, and quantum resource requirements was made possible by the encoding of binary MNIST digits (0 and 1) at image sizes of (2×2)(2\times2)(2×2), (4×4)(4\times4)(4×4), and (8×8)(8\times8)(8×8). Our findings demonstrate that, whereas QBIR-QNN offers competitive results with shallow circuits at the expense of greater qubit counts, NASS-QNN continuously converges to high training accuracy with stable parameters, achieving the most reliable and accurate performance. On the other hand, the instability and large resource overheads of FTQR-QNN and FRQCI-QNN restrict their applicability in the NISQ regime. The most promising approaches are highlighted by these results: NASS and QBIR, which provide workable trade-offs between hardware implementability, accuracy, and convergence stability.