Hybrid Classical-Quantum Transfer Learning with Noisy Quantum Circuits

D. Martín-Pérez; F. Rodríguez-Díaz; D. Gutiérrez-Avilés; A. Troncoso; F. Martínez-Álvarez

quant-phMar 17, 2026

Hybrid Classical-Quantum Transfer Learning with Noisy Quantum Circuits

Authors: D. Martín-Pérez, F. Rodríguez-Díaz, D. Gutiérrez-Avilés, A. Troncoso, F. Martínez-Álvarez

Organizations: Data Science and Big Data Lab, Pablo de Olavide University, Seville, Spain · Department of Computer Science, University of Seville, Seville, Spain

Abstract

Quantum transfer learning combines pretrained classical deep learning models with quantum circuits to reuse expressive feature representations while limiting the number of trainable parameters. In this work, we introduce a family of compact quantum transfer learning architectures that attach variational quantum classifiers to frozen convolutional backbones for image classification. We instantiate and evaluate several classical-quantum hybrid models implemented in PennyLane and Qiskit, and systematically compare them with a classical transfer-learning baseline across heterogeneous image datasets. To ensure a realistic assessment, we evaluate all approaches under both ideal simulation and noisy emulation using noise models calibrated from IBM quantum hardware specifications, as well as on real IBM quantum hardware. Experimental results show that the proposed quantum transfer learning architectures achieve competitive and, in several cases, superior accuracy while consistently reducing training time and energy consumption relative to the classical baseline. Among the evaluated approaches, PennyLane-based implementations provide the most favorable trade-off between accuracy and computational efficiency, suggesting that hybrid quantum transfer learning can offer practical benefits in realistic NISQ era settings when feature extraction remains classical.

Figures & tables

Figure 1. PennyLane ideal quantum circuit

Figure 2. Qiskit quantum circuit employing brick-wall entangling pattern (4 qubits, depth=3)

Panel of Figure 3 — Figure 3. Overview of the five evaluated architectures: classical baseline and four hybrid classical-quantum variants.

Dataset	Train	Test	Total	Difficulty	Domain
Hymenoptera [ 44 ]	245	153	398	Medium	Entomology
Brain Tumor [ 27 ]	2000	400	2400	High	Medical Imaging
Cats vs. Dogs [ 7 ]	3000	600	3600	Medium-Low	General Vision
Solar Dust [ 11 ]	240	60	300	High	Industrial

Table 1. Comprehensive dataset characteristics summary.

Component	Specification
CPU	AMD Ryzen 5 3600 (3.6 GHz, 6 cores)
RAM	24 GB DDR4-3200
Operating system	Windows 10 Pro
Python	3.13.5
PyTorch	2.1.0+cpu
TorchVision	0.16.0

Table 2. Hardware and software environment used in all experiments.

Parameter	Value
Optimizer	Adam
Learning rate ( $\eta$ )	$1\times 10^{-3}$
Adam $\beta_{1}$	0.9
Adam $\beta_{2}$	0.999
Adam $\epsilon$	$1\times 10^{-8}$
Weight decay	0 (frozen backbone)

Table 3. Unified training hyperparameters for all architectures.

Coherence properties:
Parameter	Value	Usage
$T_{1}$ (energy relaxation)	250 $\mu$ s	PL damping
$T_{2}$ (dephasing time)	150 $\mu$ s	PL dephasing
Gate timing:
Single-qubit gate time	32 ns	PL noise calc.
Two-qubit gate time (CZ)	68 ns	PL noise calc.

Table 4. IBM Heron r2 processor specifications used for noise calibration and real hardware experiments.

Parameter	Value
Backend	ibm_torino
Processor type	IBM Heron r2
Total qubits	133
Qubits used	4
Circuit depth (transpiled)	$\sim$ 49
Shots per circuit	100

Table 5. Real quantum hardware execution configuration.

Backbone	CC	PennyLane	PL-Noisy	PL-Real	Qiskit	Qiskit-Noisy	Qiskit-Real
ResNet18	0.8589 (148.9)	0.9744 (107.2)	0.9615 (178.4)	0.8421 (704)	0.9359 (305.7)	0.9295 (352.1)	0.9487 (559)
MobileNetV2	0.8846 (136.7)	0.9487 (80.7)	0.9423 (142.8)	0.8684 (685)	0.9744 (288.2)	0.9551 (331.6)	0.9103 (681)
EfficientNet-B0	0.9231 (178.9)	0.9487 (107.9)	0.9359 (168.5)	0.6579 (682)	0.9231 (297.4)	0.9103 (348.9)	0.7179 (545)
RegNet-X-400MF	0.8590 (81.0)	0.9231 (83.4)	0.9103 (128.7)	0.7895 (673)	0.9103 (270.2)	0.8974 (312.4)	0.8590 (511)

Table 6. Hymenoptera: Test accuracy and (training time in seconds) per backbone.

Dataset	CC	PennyLane	PL-Noisy	Qiskit	Qiskit-Noisy
Hymenoptera	136.4	94.8	154.6	290.4	336.3
Brain Tumor	665.7	442.2	728.3	1458.4	1685.4
Cats vs. Dogs	1024.5	665.2	1102.0	2169.1	2507.2
Solar Dust	309.5	240.1	397.2	544.6	629.6

Table 7. Average training time (s) per dataset and architecture (10 epochs, CPU).

Backbone	CC	PennyLane	PL-Noisy	Qiskit	Qiskit-Noisy
ResNet18	0.9725 (736.8)	0.9500 (541.9)	0.9425 (892.7)	0.9850 (1510.7)	0.9775 (1745.3)
MobileNetV2	0.9825 (639.3)	0.9125 (418.1)	0.9050 (687.4)	0.9725 (1447.1)	0.9600 (1672.8)
EfficientNet-B0	0.9725 (891.9)	0.9625 (476.0)	0.9525 (784.2)	0.9600 (1515.8)	0.9500 (1751.9)
RegNet-X-400MF	0.9900 (394.9)	0.9400 (332.9)	0.9350 (548.7)	0.9450 (1359.9)	0.9375 (1571.4)

Table 8. Brain Tumor: Test accuracy and training time (in seconds) per backbone.

Backbone	CC	PennyLane	PL-Noisy	Qiskit	Qiskit-Noisy
ResNet18	0.9160 (1157.5)	0.9700 (832.8)	0.9583 (1382.4)	0.9700 (2282.8)	0.9567 (2638.2)
MobileNetV2	0.9383 (979.9)	0.9800 (627.5)	0.9717 (1038.6)	0.9683 (2160.5)	0.9550 (2497.1)
EfficientNet-B0	0.9500 (1358.6)	0.9617 (740.2)	0.9500 (1224.8)	0.9650 (2226.5)	0.9517 (2573.8)
RegNet-X-400MF	0.9200 (601.8)	0.9600 (460.4)	0.9483 (762.1)	0.9617 (2006.7)	0.9450 (2319.7)

Table 9. Cats vs. Dogs: Test accuracy and (training time in seconds) per backbone.

Backbone	CC	PennyLane	PL-Noisy	Qiskit	Qiskit-Noisy
ResNet18	0.8250 (331.6)	0.8333 (257.8)	0.8167 (426.4)	0.8833 (567.4)	0.8667 (655.9)
MobileNetV2	0.8750 (300.7)	0.8667 (238.2)	0.8500 (394.1)	0.9000 (537.3)	0.8750 (621.1)
EfficientNet-B0	0.8583 (377.9)	0.8667 (251.4)	0.8417 (415.9)	0.8583 (561.5)	0.8333 (649.1)
RegNet-X-400MF	0.9250 (227.7)	0.9167 (212.9)	0.8917 (352.3)	0.8750 (512.0)	0.8500 (592.1)

Table 10. Solar Dust: Test accuracy and (training time in seconds) per backbone.

Explore similar work

Evolving Hybrid Quantum-Classical Architectures for Image Classification
Oct 2, 2026Devroop Kar, Daniel Krutz, Travis DesellHybrid Quantum-Classical ML Variational Quantum Circuits
Rochester Institute of Technology Rochester, NY 14623, USA
Investigating Quantum-Embedded Transformers on Classical Datasets for Cross-Modality Classification
Aug 7, 2026Hao-Yuan ChenHybrid Quantum-Classical ML Variational Quantum Circuits
Computer Science, University of London
Few-Shot Cross-Device Transfer for Quantum Noise Modeling on Real Hardware
Apr 27, 2026Sahil Al Farib, Sheikh Redwanul Islam, Azizur Rahman AnikFew-Shot Learning Cross-Domain Transfer Learning
United International University · Dhaka, Bangladesh

Oct 2, 2026J/K move · Enter open · S save

Evolving Hybrid Quantum-Classical Architectures for Image Classification

Devroop Kar, Daniel Krutz, Travis Desell

Rochester Institute of Technology Rochester, NY 14623, USA

Hybrid Quantum-Classical ML Variational Quantum Circuits Image Classification

Open paper AskPDF arXiv

Hybrid quantum classical neural networks integrate parameterized quantum circuits (PQCs) with established deep learning architectures, but their performance depends strongly on the choice of quantum circuit architecture, a choice that remains largely manual. Most existing approaches rely on hand-designed or fixed circuit ansätze, requiring circuit structure, gate composition, and qubit connectivity to be specified in advance with no guarantee that they suit the task. This limitation is especially acute in image classification, where quantum circuits must transform features extracted by classical networks while remaining compact enough for practical training, requirements that generic, task-agnostic ansätze are unlikely to satisfy simultaneously. We extend EXAQC, an evolutionary framework for automated quantum circuit discovery, to image classification. EXAQC evolves PQCs as intermediate processing modules while retaining classical feature-extraction and prediction layers. On MNIST, Fashion-MNIST, and CIFAR-10, EXAQC achieves 98.42%, 90.62%, and 85.47% accuracy, respectively, while using comparable gate counts to other quantum architecture-search methods. Against classical networks, evolved hybrid models maintain comparable accuracy with substantially fewer trainable parameters, reaching 85.68% on CIFAR-10 with over 25

\times

fewer parameters than a 10-layer CNN. Encoding choice also matters: rotation-based encodings (RX, RY, U3) outperform amplitude encoding by 22-25 points on CIFAR-10. These results demonstrate that automated circuit discovery yields compact quantum modules that can replace larger classical components in vision architectures while retaining competitive accuracy.

Abstract

Explore similar work

Evolving Hybrid Quantum-Classical Architectures for Image Classification

Investigating Quantum-Embedded Transformers on Classical Datasets for Cross-Modality Classification

Few-Shot Cross-Device Transfer for Quantum Noise Modeling on Real Hardware