Quantum Machine Learning for Image Classification: A Controlled Benchmark
Proceedings of the AAAI Symposium Series · 06.11.2026 · 10 (1) · 766-773
DOI: 10.1609/aaaiss.v10i1.43487 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 06.11.2026. Verfasst von Kuan Huang und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Image-based quantum machine learning usually follows a hybrid pipeline: a classical encoder compresses an image, and a quantum circuit then acts as a kernel, feature map, trainable classifier, or measurement-based readout. Yet it remains unclear which of these roles contributes useful predictive structure because prior studies often change the input representation, classical baseline, and measurement budget simultaneously. We present a controlled benchmark spanning five roles: quantum-kernel geometry, fixed product and entangled features, trainable data-reuploading representations, shot-aware probability readout, and task-adaptive Pauli measurement. Six quantum-derived methods, six matched classical controls, and two unmatched neural references are evaluated on MNIST, Fashion-MNIST, CIFAR-10, and BreastMNIST using a shared frozen ResNet-18 and train-only PCA interface. We assess exact and finite-shot inference, predictive performance, calibration, selective risk, resource requirements, and statistical reliability. PdrQC-Matched was the strongest quantum-derived method on all four datasets. C-RBF was better on Fashion-MNIST and CIFAR-10 by 2.19 and 3.50 accuracy points, while BreastMNIST showed no detectable difference. Despite lower exact accuracy, PdrQC-Matched achieved significantly lower Brier score and AURC than C-RBF on Fashion-MNIST and CIFAR-10. Finite-shot results showed no automatic benefit from entanglement or shot-aware training. Overall, image-QML conclusions depend on quantum role, measurement budget, classical control, and evaluation metric.
Zitieren
APA
Huang, K., Xu, M., & Wang, Y. (2026). Quantum Machine Learning for Image Classification: A Controlled Benchmark. Proceedings of the AAAI Symposium Series, 10(1), 766-773. https://doi.org/10.1609/aaaiss.v10i1.43487
Vancouver
Huang K, Xu M, Wang Y. Quantum Machine Learning for Image Classification: A Controlled Benchmark. Proceedings of the AAAI Symposium Series. 2026;10(1):766-773. doi:10.1609/aaaiss.v10i1.43487
BibTeX
@article{Huang2026,
author = {Huang, Kuan and Xu, Meng and Wang, Yingfeng},
title = {Quantum Machine Learning for Image Classification: A Controlled Benchmark},
journal = {Proceedings of the AAAI Symposium Series},
year = {2026},
volume = {10},
number = {1},
pages = {766--773},
doi = {10.1609/aaaiss.v10i1.43487}
}
EUVIMED