QMC-Net: Data-Aware Quantum Representations for Remote Sensing Image Classification

TL;DR

QMC-Net introduces a data-driven hybrid quantum-classical model for remote sensing image classification, utilizing channel-specific quantum circuits based on statistical features to improve accuracy over classical and existing quantum models.

Contribution

The paper presents a novel framework for designing adaptive quantum circuits based on data statistics, and introduces QMC-Net, a hybrid architecture that processes multi-channel remote sensing data more effectively.

Findings

QMC-Net achieves 93.80% and 99.34% accuracy on EuroSAT and SAT-6 datasets.

A residual-enhanced variant improves accuracy to 94.69% and 99.39%.

QMC-Net outperforms classical baselines and monolithic hybrid quantum models.

Abstract

Hybrid quantum-classical models offer a promising route for learning from complex data; however, their application to multi-band remote sensing imagery often relies on generic, data-agnostic quantum circuits that fail to account for channel-specific statistical variability. In this work, we propose a data-driven framework that maps band-level statistics such as Shannon Entropy, Variance, Spectral Flatness, and Edge Density to the hyperparameters of customized quantum circuits. Building on this framework, we introduce QMC-Net, a hybrid architecture that processes six data channels using band-specific quantum circuits, enabling adaptive quantum feature encoding and transformation across channels. Experiments on the EuroSAT and SAT-6 datasets demonstrate that QMC-Net achieves accuracies of 93.80 % and 99.34 %, respectively, while a residual-enhanced variant further improves performance to 94.69 % and 99.39 %. These results consistently outperform strong classical baselines and monolithic hybrid quantum models, highlighting the effectiveness of data-aware quantum circuit design under NISQ constraints.