Hybrid Quantum Neural Networks with Group Averaging for Image Classification
Entropy · 22.10.2026 · 28 (11) · 1171
DOI: 10.3390/e28111171 ↗Kurz gefasst
Fachartikel in der Zeitschrift Entropy, online erschienen am 22.10.2026. Verfasst von Yujing Fan und 4 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Shandong Provincial Natural Science Foundation, Youth Innovation Team Program of Shandong Province.
Abstract (Originalsprache)
The growing real-world deployment of computer vision technologies imposes increasingly stringent requirements on the generalization and few-shot adaptation performance of image classification models. While quantum machine learning (QML) has shown considerable promise for image classification tasks, existing hybrid quantum neural networks (HQNNs) consistently exhibit limited generalization ability and weak few-shot learning performance. We investigate the integration of standard W-group averaging into two existing HQNN architectures, HQNN-Parallel and HQNN-Quanv. Each complete input image is transformed by the four elements of the W-group and processed through a shared-parameter feature extractor. The resulting quantum feature vectors or feature maps are averaged before the final classical classification layer. This construction introduces no additional trainable parameters, but requires four transformed-input evaluations per image. The resulting models are denoted as W-HQNN-Parallel and W-HQNN-Quanv, respectively. Systematic experiments on three classic image classification datasets show that the W-HQNN-Parallel model achieves an accuracy of approximately 91.56% on the full FashionMNIST dataset and 73.96% on the full CIFAR-10 dataset respectively, outperforming the original model by around 0.50 and 2.88 percentage points, while also yielding lower test loss than HQNN-Parallel on both datasets. In single-run reduced-data experiments, W-HQNN-Quanv achieved accuracies of 68.83% on MNIST and 64.19% on FashionMNIST, exceeding the corresponding baselines by 9.60 and 6.16 percentage points, respectively. These results provide empirical evidence of the effects of W-group averaging in the two investigated HQNN architectures under the evaluated experimental settings.
Förderung
- National Natural Science Foundation of China
- Shandong Provincial Natural Science Foundation
- Youth Innovation Team Program of Shandong Province
Zitieren
APA
Fan, Y., Teng, H., Chen, X., Wang, S., & Ma, H. (2026). Hybrid Quantum Neural Networks with Group Averaging for Image Classification. Entropy, 28(11), 1171. https://doi.org/10.3390/e28111171
Vancouver
Fan Y, Teng H, Chen X, Wang S, Ma H. Hybrid Quantum Neural Networks with Group Averaging for Image Classification. Entropy. 2026;28(11):1171. doi:10.3390/e28111171
BibTeX
@article{Fan2026,
author = {Fan, Yujing and Teng, Huanfeng and Chen, Xiang and Wang, Shumei and Ma, Hongyang},
title = {Hybrid Quantum Neural Networks with Group Averaging for Image Classification},
journal = {Entropy},
year = {2026},
volume = {28},
number = {11},
pages = {1171},
doi = {10.3390/e28111171}
}
EUVIMED