aiqbench analysis
This study demonstrates that while variational quantum classifiers using linear readouts struggle to outperform classical baselines, the underlying quantum feature maps can significantly boost performance when integrated into kernel-based decision frameworks. The research highlights a critical saturation effect where increasing qubit counts does not yield proportional gains due to mismatches between Hilbert space dimension and parameter scaling. Ultimately, meaningful advantages in multispectral land-cover classification emerge from hybridizing learned quantum representations with classical mechanisms rather than attempting direct model replacement.
Parameterized Quantum Circuits as Feature Maps: Representation Quality and Readout Effects in Multispectral Land-Cover Classification
arXiv:2604.26675v2 Announce Type: replace Abstract: We investigate variational quantum classifiers (VQCs) for land-cover classification from multispectral satellite imagery, adopting a feature-map perspective in which the quantum circuit defines a nonlinear data embedding while the readout determines how this representation is exploited. Using the EuroSAT-MS dataset, we perform a systematic one-vs-one evaluation across all class pairs under a controlled experimental protocol, comparing classical baselines (logistic regression, SVMs, neural networks) with VQCs employing both linear readout and quantum-kernel SVM strategies. Our results show that, while VQCs with linear readout do not outperform strong classical baselines such as RBF-SVM, the same trained quantum feature map can significantly improve performance when reused within a kernel-based decision framework. A qubit-count sweep further reveals saturation effects consistent with the mismatch between exponential Hilbert space dimension and linear parameter scaling. Overall, our findings highlight that the effectiveness of quantum models depends critically on the interplay between representation and readout, and that meaningful gains may arise from combining learned quantum feature maps with classical decision mechanisms rather than seeking direct replacement of classical models.
Abstract:We investigate variational quantum classifiers (VQCs) for land-cover classification from multispectral satellite imagery, adopting a feature-map perspective in which the quantum circuit defines a nonlinear data embedding while the readout determines how this representation is exploited. Using the EuroSAT-MS dataset, we perform a systematic one-vs-one evaluation across all class pairs under a controlled experimental protocol, comparing classical baselines (logistic regression, SVMs, neural networks) with VQCs employing both linear readout and quantum-kernel SVM strategies. Our results show that, while VQCs with linear readout do not outperform strong classical baselines such as RBF-SVM, the same trained quantum feature map can significantly improve performance when reused within a kernel-based decision framework. A qubit-count sweep further reveals saturation effects consistent with the mismatch between exponential Hilbert space dimension and linear parameter scaling. Overall, our findings highlight that the effectiveness of quantum models depends critically on the interplay between representation and readout, and that meaningful gains may arise from combining learned quantum feature maps with classical decision mechanisms rather than seeking direct replacement of classical models.
Quantum Physics (quant-ph); Machine Learning (cs.LG)
arXiv:2604.26675 [quant-ph]
(or arXiv:2604.26675v2 [quant-ph] for this version)
https://doi.org/10.48550/arXiv.2604.26675 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 266 words
Related coverage
SQUARE: Structured Quantum Representation Adapters as Compact Quadratic Feature Maps for Frozen Language Models
arXiv · Sep 30, 2026
Chinese Academy of Sciences’ PQFA Cuts Multimodal Model Parameters by 10×
Quantum Zeitgeist · Jul 30, 2026
OQC And Trust Base Study Helps Map The Path to Quantum Advantage in Finance
The Quantum Insider · Sep 17, 2026
Quantum Circuits Cut Data Imbalance Recall Gap by 10–25%
Quantum Zeitgeist · Jul 13, 2026