Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2307.16723

Hybrid quantum transfer learning for crack image classification on NISQ hardware

Alexander Geng, Ali Moghiseh, Claudia Redenbach, Katja Schladitz

Published Jul 31, 2023• 1 citation
arXivHTMLPDF

Abstract

Quantum computers possess the potential to process data using a remarkably reduced number of qubits compared to conventional bits, as per theoretical foundations. However, recent experiments have indicated that the practical feasibility of retrieving an image from its quantum encoded version is currently limited to very small image sizes. Despite this constraint, variational quantum machine learning algorithms can still be employed in the current noisy intermediate scale quantum (NISQ) era. An example is a hybrid quantum machine learning approach for edge detection. In our study, we present an application of quantum transfer learning for detecting cracks in gray value images. We compare the performance and training time of PennyLane's standard qubits with IBM's qasm\_simulator and real backends, offering insights into their execution efficiency.

DOI
10.48550/arxiv.2307.16723

Related papers

Hybrid quantum transfer learning for crack image classification on NISQ hardware

Alexander Geng, Ali Moghiseh, Claudia Redenbach +1 more

Quantum computers offer the potential to process data using significantly fewer qubits compared to conventional bits, as per theoretical foundations. However, recent experiments [1] have indicated that the practical feasibility of retrieving an image from its quantum encoded version is currently limited to very small image sizes. Despite this constraint, variational quantum machine learning algorithms can still be employed in the current noisy intermediate scale quantum (NISQ) era. An example is a hybrid quantum machine learning approach for edge detection [2]. In our study, we showcase an application of quantum transfer learning for detecting cracks in gray value images. We evaluate the performance and training time of PennyLane’s standard qubits with IBM’s qasm_simulator and real backends, offering insights into their execution efficiency.

AIP conference proceedings•Jan 1, 2025•6 citations

A hybrid quantum image edge detector for the NISQ era

Alexander Geng, Ali Moghiseh, Claudia Redenbach +1 more

Abstract Edges are image locations where the gray value intensity changes suddenly. They are among the most important features to understand and segment an image. Edge detection is a standard task in digital image processing, solved, for example, using filtering techniques. However, the amount of data to be processed grows rapidly and pushes even supercomputers to their limits. Quantum computing promises exponentially lower memory usage in terms of the number of qubits compared to the number of classical bits. In this paper, we propose a hybrid method for quantum edge detection based on the idea of a quantum artificial neuron. Our method can be practically implemented on quantum computers, especially on those of the current noisy intermediate-scale quantum era. We compare six variants of the method to reduce the number of circuits and thus the time required for the quantum edge detection. Taking advantage of the scalability of our method, we can practically detect edges in images considerably larger than reached before.

arXiv:2203.12072•Quantum Machine Intelligence•Jun 23, 2022•21 citations

Hybrid Classical-Quantum Transfer Learning with Noisy Quantum Circuits

D. Martín-Pérez, F. Rodríguez-Díaz, D. Gutiérrez-Avilés +2 more

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.

quant-pharXiv:2603.16973•Computer Modeling in Engineering & Sciences•Mar 18, 2026•1 citation

Post-Variational Quantum Neural Networks on a Hybrid HPC-QC System

Maxence Vandromme, Miwako Tsuji

We implement a post-variational quantum neural network on a real HPC-QC system and show the feasibility of fully training this class of algorithms on current Noisy Intermediate-Scale Quantum (NISQ) devices, which are limited by noise, low number of qubits, and scarcity. Post-variational methods are hybrid classical-quantum Machine Learning algorithms that remove the need for quantum circuits evaluations during training, thus making them more suited to the availability constraints of physical quantum devices. We investigate the scalability of the algorithm to a higher number of qubits, larger datasets, and more elaborate models, giving insight for more efficient implementation. Experiments for an image classification task on a cutting-edge HPC-QC system show that post-variational quantum neural networks are fully trainable in reasonable times on a superconducting device. The models trained also show performance at least comparable to a variational approach, with one configuration showing a significant improvement in classification accuracy.

International Conference for High Performance Computing, Networking, Storage and Analysis (SC)•Nov 7, 2025•2 citations

Transfer learning in hybrid classical-quantum neural networks

Andrea Mari, Thomas R. Bromley, Josh Izaac +2 more

We extend the concept of transfer learning, widely applied in modern machine learning algorithms, to the emerging context of hybrid neural networks composed of classical and quantum elements. We propose different implementations of hybrid transfer learning, but we focus mainly on the paradigm in which a pre-trained classical network is modified and augmented by a final variational quantum circuit. This approach is particularly attractive in the current era of intermediate-scale quantum technology since it allows to optimally pre-process high dimensional data (e.g., images) with any state-of-the-art classical network and to embed a select set of highly informative features into a quantum processor. We present several proof-of-concept examples of the convenient application of quantum transfer learning for image recognition and quantum state classification. We use the cross-platform software library PennyLane to experimentally test a high-resolution image classifier with two different quantum computers, respectively provided by IBM and Rigetti.

arXiv:1912.08278•Quantum•Oct 9, 2020•436 citations

Hybrid Quantum-Classical Neural Networks For Efficient Image Classification On Small Datasets

Dr CH Pavan Satish, P Indu, P Jahnavi +2 more

The modern deep learning models such as CNNs and Transformer models are very good at prediction but too big, require a truckload of computing resources, lots of data, and lots of memory so difficult to run on a budget laptop or a cheap smartphone.Quantum computing is an entirely different animal that is capable of handling information in large Hilbert spaces due to the ability of superposition and entanglement.I discuss a Hybrid Quantum Classical Neural Network (HQ-NN) in this paper, which combines the use of parameterised quantum circuits in a small stage of feature extraction, and a conventional fully-connected network in the actual predictions and optimisation.The quantum bit executes Aashna as an angle encoding of a flat image which the quantum encodes before executing a series of parameterised rotations together with CNOTs on the entangled bits and retrieves expectation values back as a classical feature-vector.The end-to-end training of the entire thing is a differentiable junction between the PennyLane and PyTorch implementations, and therefore the gradients flow straight across the quantum implementation.The new design and purely the quantum circuit outperform each other with an approximate 10 -percent difference in accuracy and a percentage difference of 20 -percent on general image benchmarks, which is a fraction of the number of parameters in a pure classical model.In even the case of adding simulated quantum noise, the predictions remain consistent to acceptable levels, indicating that this concept can be maintained on even real Noisy Intermediate-Scale Quantum (NISQ) machines.

International journal of engineering science and advanced technology.•Mar 1, 2026•0 citations
Quantum computers possess the potential to process data using a remarkably reduced number of qubits compared to conventional bits, as per theoretical foundations. However, recent experiments have indicated that the practical feasibility of retrieving an image from its quantum encoded version is currently limited to very small image sizes. Despite this constraint, variational quantum machine learning algorithms can still be employed in the current noisy intermediate scale quantum (NISQ) era. An example is a hybrid quantum machine learning approach for edge detection. In our study, we present an application of quantum transfer learning for detecting cracks in gray value images. We compare the performance and training time of PennyLane's standard qubits with IBM's qasm_simulator and real backends, offering insights into their execution efficiency.
Quantum computers offer the potential to process data using significantly fewer qubits compared to conventional bits, as per theoretical foundations. However, recent experiments [1] have indicated that the practical feasibility of retrieving an image from its quantum encoded version is currently limited to very small image sizes. Despite this constraint, variational quantum machine learning algorithms can still be employed in the current noisy intermediate scale quantum (NISQ) era. An example is a hybrid quantum machine learning approach for edge detection [2]. In our study, we showcase an application of quantum transfer learning for detecting cracks in gray value images. We evaluate the performance and training time of PennyLane’s standard qubits with IBM’s qasm_simulator and real backends, offering insights into their execution efficiency.
Abstract Edges are image locations where the gray value intensity changes suddenly. They are among the most important features to understand and segment an image. Edge detection is a standard task in digital image processing, solved, for example, using filtering techniques. However, the amount of data to be processed grows rapidly and pushes even supercomputers to their limits. Quantum computing promises exponentially lower memory usage in terms of the number of qubits compared to the number of classical bits. In this paper, we propose a hybrid method for quantum edge detection based on the idea of a quantum artificial neuron. Our method can be practically implemented on quantum computers, especially on those of the current noisy intermediate-scale quantum era. We compare six variants of the method to reduce the number of circuits and thus the time required for the quantum edge detection. Taking advantage of the scalability of our method, we can practically detect edges in images considerably larger than reached before.
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.
We implement a post-variational quantum neural network on a real HPC-QC system and show the feasibility of fully training this class of algorithms on current Noisy Intermediate-Scale Quantum (NISQ) devices, which are limited by noise, low number of qubits, and scarcity. Post-variational methods are hybrid classical-quantum Machine Learning algorithms that remove the need for quantum circuits evaluations during training, thus making them more suited to the availability constraints of physical quantum devices. We investigate the scalability of the algorithm to a higher number of qubits, larger datasets, and more elaborate models, giving insight for more efficient implementation. Experiments for an image classification task on a cutting-edge HPC-QC system show that post-variational quantum neural networks are fully trainable in reasonable times on a superconducting device. The models trained also show performance at least comparable to a variational approach, with one configuration showing a significant improvement in classification accuracy.
We extend the concept of transfer learning, widely applied in modern machine learning algorithms, to the emerging context of hybrid neural networks composed of classical and quantum elements. We propose different implementations of hybrid transfer learning, but we focus mainly on the paradigm in which a pre-trained classical network is modified and augmented by a final variational quantum circuit. This approach is particularly attractive in the current era of intermediate-scale quantum technology since it allows to optimally pre-process high dimensional data (e.g., images) with any state-of-the-art classical network and to embed a select set of highly informative features into a quantum processor. We present several proof-of-concept examples of the convenient application of quantum transfer learning for image recognition and quantum state classification. We use the cross-platform software library PennyLane to experimentally test a high-resolution image classifier with two different quantum computers, respectively provided by IBM and Rigetti.
The modern deep learning models such as CNNs and Transformer models are very good at prediction but too big, require a truckload of computing resources, lots of data, and lots of memory so difficult to run on a budget laptop or a cheap smartphone.Quantum computing is an entirely different animal that is capable of handling information in large Hilbert spaces due to the ability of superposition and entanglement.I discuss a Hybrid Quantum Classical Neural Network (HQ-NN) in this paper, which combines the use of parameterised quantum circuits in a small stage of feature extraction, and a conventional fully-connected network in the actual predictions and optimisation.The quantum bit executes Aashna as an angle encoding of a flat image which the quantum encodes before executing a series of parameterised rotations together with CNOTs on the entangled bits and retrieves expectation values back as a classical feature-vector.The end-to-end training of the entire thing is a differentiable junction between the PennyLane and PyTorch implementations, and therefore the gradients flow straight across the quantum implementation.The new design and purely the quantum circuit outperform each other with an approximate 10 -percent difference in accuracy and a percentage difference of 20 -percent on general image benchmarks, which is a fraction of the number of parameters in a pure classical model.In even the case of adding simulated quantum noise, the predictions remain consistent to acceptable levels, indicating that this concept can be maintained on even real Noisy Intermediate-Scale Quantum (NISQ) machines.