QMC-Net: Data-Aware Quantum Representations for Remote Sensing Image Classification
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914517432139776 |
|---|---|
| author | Hossain, Md Aminur Patel, Ayush V. Banerjee, Biplab |
| author_facet | Hossain, Md Aminur Patel, Ayush V. Banerjee, Biplab |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_11817 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | QMC-Net: Data-Aware Quantum Representations for Remote Sensing Image Classification Hossain, Md Aminur Patel, Ayush V. Banerjee, Biplab Quantum Physics Computer Vision and Pattern Recognition 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. |
| title | QMC-Net: Data-Aware Quantum Representations for Remote Sensing Image Classification |
| topic | Quantum Physics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.11817 |