Feature-Adaptive Fusion in Hybrid Quantum-Classical Neural Networks for Robust Biomedical Image Classification
Abstract
Hybrid quantum-classical neural networks provide a promising approach for incorporating quantum circuits into machine learning in the noisy intermediate-scale quantum regime. However, existing hybrid models often rely on fixed or globally shared fusion strategies, which may limit their ability to exploit complementary information carried by quantum branches, especially under distribution shifts. In this work, we propose a Feature-Adaptive Fusion Hybrid Quantum-Classical Neural Network (FAF-HQNN) for biomedical image classification. The model combines a classical deep feature encoder with a variational quantum circuit (VQC) and introduces a feature-adaptive fusion mechanism to dynamically weight classical and quantum predictions. We evaluate FAF-HQNN on two MedMNIST benchmarks, PathMNIST and BloodMNIST, under clean and corrupted test conditions. FAF-HQNN achieves the strongest overall performance on clean data among the compared methods and shows improved robustness under Gaussian, salt-and-pepper, and Poisson corruptions. Further analysis of circuit layout, measurement basis, and depth shows that even shallow variational quantum circuits can provide useful complementary information. These results demonstrate that feature-adaptive fusion is an effective strategy for improving accuracy and robustness in hybrid quantum-classical models for biomedical image classification.
Related
- Quantum Feature Selection for Biomedical Data Analysis
- Does the Readout Bypass Leak the Input? A Feature-Visibility Audit of Hybrid Quantum-Classical Models
- The ZZ feature map induces a signless Laplacian metric: a closed-form classical surrogate for quantum kernel regression
- Cover Feature: Stress‐Programmed Microcrack Networks in Gallium–Carbon Nanotube Thin Films for Plasma‐Active and Electroresponsive Antibacterial Interfaces (Small Struct. 10/2026)
- Benchmarking Quantum Feature Encoding Strategies for Binary Classification with QSVM
BibTeX
@misc{hou2026featureadaptive,
title = {{Feature-Adaptive Fusion in Hybrid Quantum-Classical Neural Networks for Robust Biomedical Image Classification}},
author = {Yan-Yan Hou and Jian Li and Chongqiang Ye and Hengji Li and Zhuo Wang and Qinghui Liu},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.15267},
eprint = {2609.15267},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.15267},
}
RIS
TY - UNPB
TI - Feature-Adaptive Fusion in Hybrid Quantum-Classical Neural Networks for Robust Biomedical Image Classification
AU - Yan-Yan Hou
AU - Jian Li
AU - Chongqiang Ye
AU - Hengji Li
AU - Zhuo Wang
AU - Qinghui Liu
PY - 2026
DA - 2026/09/14
PB - arXiv
DO - 10.48550/arxiv.2609.15267
UR - https://arxiv.org/abs/2609.15267
AB - Hybrid quantum-classical neural networks provide a promising approach for incorporating quantum circuits into machine learning in the noisy intermediate-scale quantum regime. However, existing hybrid models often rely on fixed or globally shared fusion strategies, which may limit their ability to exploit complementary information carried by quantum branches, especially under distribution shifts. In this work, we propose a Feature-Adaptive Fusion Hybrid Quantum-Classical Neural Network (FAF-HQNN) for biomedical image classification. The model combines a classical deep feature encoder with a variational quantum circuit (VQC) and introduces a feature-adaptive fusion mechanism to dynamically weight classical and quantum predictions. We evaluate FAF-HQNN on two MedMNIST benchmarks, PathMNIST and BloodMNIST, under clean and corrupted test conditions. FAF-HQNN achieves the strongest overall performance on clean data among the compared methods and shows improved robustness under Gaussian, salt-and-pepper, and Poisson corruptions. Further analysis of circuit layout, measurement basis, and depth shows that even shallow variational quantum circuits can provide useful complementary information. These results demonstrate that feature-adaptive fusion is an effective strategy for improving accuracy and robustness in hybrid quantum-classical models for biomedical image classification.
ER -