Towards Fair Benchmarking of Quantum Transfer Learning for Visual Classification

• URL: http://arxiv.org/abs/2605.19417v1
• Date: Tue, 19 May 2026 06:10:32 GMT
• Title: Towards Fair Benchmarking of Quantum Transfer Learning for Visual Classification
• Abstract summary: Quantum Transfer Learning offers a promising approach for visual quantum machine learning under near-term constraints.<n>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.<n>This work presents a controlled benchmarking methodology for evaluating representative QTL methods under a unified transfer-learning pipeline.
• Score: 2.417944170423441
• License: http://creativecommons.org/licenses/by/4.0/
• 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 papers

• Fisher information based lower bounds on the cost of quantum phase estimation [0.0]
  Quantum phase estimation (QPE) is a cornerstone of quantum algorithms designed to estimate the eigenvalues of a unitary operator.<n>Existing performance assessments fail to separate the statistical information inherent in the quantum circuit from the efficiency of classical post-processing.<n>We employ Fisher information and the Cramer-Rao lower bound to formulate the performance limits of circuit designs.
  arXiv  Detail & Related papers  (2026-03-13T06:40:12Z)
• AQER: a scalable and efficient data loader for digital quantum computers [62.40228216126285]
  We develop AQER, a scalable AQL method that constructs the loading circuit by systematically reducing entanglement in target states.<n>We conduct systematic experiments to evaluate the effectiveness of AQER, using synthetic datasets, classical image and language datasets, and a quantum many-body state datasets with up to 50 qubits.
  arXiv  Detail & Related papers  (2026-02-02T14:39:42Z)
• Continual Quantum Architecture Search with Tensor-Train Encoding: Theory and Applications to Signal Processing [68.35481158940401]
  CL-QAS is a continual quantum architecture search framework.<n>It mitigates challenges of costly encoding amplitude and forgetting in variational quantum circuits.<n>It achieves controllable robustness expressivity, sample-efficient generalization, and smooth convergence without barren plateaus.
  arXiv  Detail & Related papers  (2026-01-10T02:36:03Z)
• Domain-Aware Quantum Circuit for QML [0.7999703756441755]
  We present a Domain-Aware Quantum Circuit (DAQC) that leverages image priors to guide locality-preserving encoding and entanglement.<n>The design employs interleaved encode--train cycles, where entanglement is applied among qubits hosting neighboring pixels, aligned to device connectivity.<n>We evaluate DAQC on MNIST, FashionMentangle, and PneumoniaMNIST datasets.
  arXiv  Detail & Related papers  (2025-12-19T17:02:58Z)
• ConQuER: Modular Architectures for Control and Bias Mitigation in IQP Quantum Generative Models [40.972673943861075]
  Quantum generative models based on instantaneous quantum (IQP) circuits show great promise in learning complex distributions.<n>Current implementations suffer from lack of controllability over generated outputs and severe generation bias towards certain expected patterns.<n>We present a Controllable Quantum Generative Framework, ConQuER, which addresses both challenges through a modular circuit architecture.
  arXiv  Detail & Related papers  (2025-09-26T16:32:41Z)
• End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost [53.25965863436039]
  Quantization-aware training (QAT) provides a more principled solution, but its reliance on backpropagation incurs prohibitive memory costs.<n>We propose ZeroQAT, a zeroth-order optimization-based QAT framework that supports both weight and activation quantization.<n>Experiments show that ZeroQAT consistently outperforms representative PTQ and QAT baselines while requiring significantly less memory.
  arXiv  Detail & Related papers  (2025-08-21T01:18:27Z)
• VQC-MLPNet: An Unconventional Hybrid Quantum-Classical Architecture for Scalable and Robust Quantum Machine Learning [50.95799256262098]
  Variational quantum circuits (VQCs) hold promise for quantum machine learning but face challenges in expressivity, trainability, and noise resilience.<n>We propose VQC-MLPNet, a hybrid architecture where a VQC generates the first-layer weights of a classical multilayer perceptron during training, while inference is performed entirely classically.
  arXiv  Detail & Related papers  (2025-06-12T01:38:15Z)
• BenchQC: A Benchmarking Toolkit for Quantum Computation [0.4037357056611557]
  Variational Quantum Eigensolver (VQE) is a promising algorithm for quantum computing applications in chemistry and materials science.<n>This study benchmarks the performance of the VQE for calculating ground-state energies of aluminum clusters.
  arXiv  Detail & Related papers  (2025-02-13T18:51:08Z)
• Unifying (Quantum) Statistical and Parametrized (Quantum) Algorithms [65.268245109828]
  We take inspiration from Kearns' SQ oracle and Valiant's weak evaluation oracle. We introduce an extensive yet intuitive framework that yields unconditional lower bounds for learning from evaluation queries.
  arXiv  Detail & Related papers  (2023-10-26T18:23:21Z)
• Pre-training Tensor-Train Networks Facilitates Machine Learning with Variational Quantum Circuits [70.97518416003358]
  Variational quantum circuits (VQCs) hold promise for quantum machine learning on noisy intermediate-scale quantum (NISQ) devices. While tensor-train networks (TTNs) can enhance VQC representation and generalization, the resulting hybrid model, TTN-VQC, faces optimization challenges due to the Polyak-Lojasiewicz (PL) condition. To mitigate this challenge, we introduce Pre+TTN-VQC, a pre-trained TTN model combined with a VQC.
  arXiv  Detail & Related papers  (2023-05-18T03:08:18Z)
• When BERT Meets Quantum Temporal Convolution Learning for Text Classification in Heterogeneous Computing [75.75419308975746]
  This work proposes a vertical federated learning architecture based on variational quantum circuits to demonstrate the competitive performance of a quantum-enhanced pre-trained BERT model for text classification. Our experiments on intent classification show that our proposed BERT-QTC model attains competitive experimental results in the Snips and ATIS spoken language datasets.
  arXiv  Detail & Related papers  (2022-02-17T09:55:21Z)
• Ansatz-Independent Variational Quantum Classifier [0.0]
  We show that variational quantum classifiers (VQCs) fit inside the well-known kernel method. We also propose a variational circuit realization (VCR) for designing efficient quantum circuits for a given unitary operator.
  arXiv  Detail & Related papers  (2021-02-02T21:25:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.