Towards Fair Benchmarking of Quantum Transfer Learning for Visual Classification
Abstract
Quantum Transfer Learning (QTL) offers a promising approach for visual quantum machine learning under near-term constraints, where limited qubit counts, shallow circuit depths, and costly hybrid optimization restrict end-to-end quantum training. In this setting, pretrained classical backbones can extract high-level visual features, while compact quantum modules operate as trainable classification heads. However, existing QTL results are difficult to compare because they often differ in datasets, preprocessing, backbone settings, qubit budgets, circuit designs, optimization choices, and reporting protocols. This work presents a controlled benchmarking methodology for evaluating representative QTL methods under a unified transfer-learning pipeline. The benchmark compares DQN-QTL, QPIE-QTL, AE-CQTL, PVCQTL, and ED-QTL under shared preprocessing rules, frozen-backbone settings, training conditions, and reporting metrics. The evaluation focuses on Fashion-MNIST and Hymenoptera Ants vs. Bees as the two main datasets, while CIFAR-10 is used to provide additional configuration-level evidence on a harder natural-image task. Beyond predictive performance, the benchmark analyzes circuit size, trainable parameters, quantum parameters, training time, and architectural sensitivity to qubit count and circuit depth. The results show that no single QTL family dominates across all settings: performance depends on the dataset, encoding strategy, circuit design, and computational cost. These findings highlight the need for resource-aware QTL evaluation and provide guidance for selecting hybrid quantum-classical transfer models under near-term resource constraints.
Related
- Benchmarking Quantum Feature Encoding Strategies for Binary Classification with QSVM
- Facial classification Using Hybrid Quantum Machine Learning
- Object Detection Using Quantum Transfer Learning
- Sample-Size Scalability and Representation Sensitivity of Quantum Machine Learning Models for Higgs Boson Event Classification
- HyQ-LC: Improving Light-Curve Classification with Hybrid Quantum--Classical Learning
BibTeX
@misc{innan2026towards,
title = {{Towards Fair Benchmarking of Quantum Transfer Learning for Visual Classification}},
author = {Nouhaila Innan and Saim Rehman and Muhammad Shafique},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2605.19417},
eprint = {2605.19417},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.19417},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Towards Fair Benchmarking of Quantum Transfer Learning for Visual Classification
AU - Nouhaila Innan
AU - Saim Rehman
AU - Muhammad Shafique
PY - 2026
DA - 2026/10/24
PB - arXiv
DO - 10.48550/arxiv.2605.19417
UR - https://arxiv.org/abs/2605.19417
AB - Quantum Transfer Learning (QTL) offers a promising approach for visual quantum machine learning under near-term constraints, where limited qubit counts, shallow circuit depths, and costly hybrid optimization restrict end-to-end quantum training. In this setting, pretrained classical backbones can extract high-level visual features, while compact quantum modules operate as trainable classification heads. However, existing QTL results are difficult to compare because they often differ in datasets, preprocessing, backbone settings, qubit budgets, circuit designs, optimization choices, and reporting protocols. This work presents a controlled benchmarking methodology for evaluating representative QTL methods under a unified transfer-learning pipeline. The benchmark compares DQN-QTL, QPIE-QTL, AE-CQTL, PVCQTL, and ED-QTL under shared preprocessing rules, frozen-backbone settings, training conditions, and reporting metrics. The evaluation focuses on Fashion-MNIST and Hymenoptera Ants vs. Bees as the two main datasets, while CIFAR-10 is used to provide additional configuration-level evidence on a harder natural-image task. Beyond predictive performance, the benchmark analyzes circuit size, trainable parameters, quantum parameters, training time, and architectural sensitivity to qubit count and circuit depth. The results show that no single QTL family dominates across all settings: performance depends on the dataset, encoding strategy, circuit design, and computational cost. These findings highlight the need for resource-aware QTL evaluation and provide guidance for selecting hybrid quantum-classical transfer models under near-term resource constraints.
ER -