EUVIMEDEUVIMED entdecken
Crossref

QMDUC: quantum multi-channel data uploading convolution for image classification

Han Qi, Shengjun Wang, Hao Wang, Abdullah Gani, Lip Yee Por

Physica Scripta · 10.04.2026 · 101 (14) · 145102

DOI: 10.1088/1402-4896/ae5579 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physica Scripta, online erschienen am 02.04.2026. Verfasst von Han Qi und 4 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Gefördert von: Liaoning Provincial Department of Education Research, Scientific Research Foundation for Advanced Talents from Shenyang Aerospace University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hybrid Quantum-Classical Convolutional Neural Networks (HQCNNs) show significant potential for image classification by embedding quantum circuits as convolutional kernels within classical CNNs, leveraging quantum computing to enhance feature extraction. While this approach provides a feasible pathway toward achieving quantum advantage under current Noisy Intermediate-Scale Quantum (NISQ) hardware constraints, existing HQCNNs face critical challenges, including limited classification accuracy and excessive quantum resource consumption when processing multi-channel data. To address these issues, this paper proposes the Quantum Multi-channel Data Uploading Convolution (QMDUC) method, which employs data re-uploading techniques to optimize quantum data encoding strategies, significantly reducing qubit requirements while maintaining complex data processing capabilities. QMDUC supports two encoding modes: Channel-Priority QMDUC (CP-QMDUC) and Data-Priority QMDUC (DP-QMDUC), enabling flexible trade-offs between qubit count and circuit depth, thereby providing adaptive solutions tailored to different quantum hardware constraints. Experimental validation on the CIFAR-10 three-channel color image dataset and Fashion-MNIST single-channel grayscale image dataset demonstrates that QMDUC significantly outperforms existing HQCNN methods in both classification accuracy and quantum resource efficiency. Specifically, under low-resource configurations, the proposed method achieves an approximate reduction in qubit requirements of 75%–95% while maintaining comparable or superior accuracy; under higher-resource configurations, it achieves approximately 10% improvement in peak accuracy with comparable qubit consumption to existing methods, providing an effective technical pathway for practical applications of quantum machine learning in computer vision.

Förderung

  • Liaoning Provincial Department of Education Research
  • Scientific Research Foundation for Advanced Talents from Shenyang Aerospace University

Zitieren

APA

Qi, H., Wang, S., Wang, H., Gani, A., & Por, L. Y. (2026). QMDUC: quantum multi-channel data uploading convolution for image classification. Physica Scripta, 101(14), 145102. https://doi.org/10.1088/1402-4896/ae5579

Vancouver

Qi H, Wang S, Wang H, Gani A, Por LY. QMDUC: quantum multi-channel data uploading convolution for image classification. Physica Scripta. 2026;101(14):145102. doi:10.1088/1402-4896/ae5579

BibTeX
@article{Qi2026,
  author = {Qi, Han and Wang, Shengjun and Wang, Hao and Gani, Abdullah and Por, Lip Yee},
  title = {QMDUC: quantum multi-channel data uploading convolution for image classification},
  journal = {Physica Scripta},
  year = {2026},
  volume = {101},
  number = {14},
  pages = {145102},
  doi = {10.1088/1402-4896/ae5579}
}
Kostenlos starten →