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

Quantum Science and Technology

Variational quantum circuits for convolution and window-based image processing applications

Hasan Yetış, Mehmet Karaköse

Published Jul 3, 2023• 7 citations
Publisher

Abstract

Abstract Quantum information processing is gaining popularity in the fields of machine learning and image processing because of its advantages. Quantum convolution is an interesting topic in this field, and studies on this topic can be divided into value-based and angle-based methods. Although quantum convolution studies on angle-based or variational quantum circuits (VQCs) is called convolution, the circuits work differently from classical convolution. In this study, contrary to the literature, the VQC was trained to imitate classical convolution. The differential evolution algorithm (DEA) was used to optimize the VQCs. The proposed method requires as many qubits as the filter size (N× N). The generated circuits contain N× N× 4 quantum gates and N× N × 3 trainable parameters. The generated circuits were tested in Python environment using Cirq simulator. The Cifar10 and MNIST datasets are used as examples. For 2 × 2 filters with different weights, the convolution was successfully modeled with a mean squared error of less than 0.001. In general, the proposed method imitates classic convolution within ± 5 % tolerance. In conclusion, VQCs that imitate classical convolution with fewer qubits and quantum gates than value-based methods were obtained.

DOI
10.1088/2058-9565/ace378

Related papers

A New Framework Containing Convolution and Pooling Circuits for Image Processing and Deep Learning Applications with Quantum Computing Implementation

Hasan Yetış, Mehmet Karaköse

The resource need for deep learning and quantum computers' high computing power potential encourage collaboration between the two fields. Today, variational quantum circuits are used to perform the convolution operation with quantum computing. However, the results produced by variational circuits do not show a direct resemblance to the classical convolution operation. Because classical data is encoded into quantum data with their exact values in value-encoded methods, in contrast to variational quantum circuits, arithmetical operations can be applied with high accuracy. In this study, value-encoded quantum circuits for convolution and pooling operations are proposed to apply deep learning in quantum computers in a traditional and proven way. To construct the convolution and pooling operations, some modules such as addition, multiplication, division, and comparison are created. In addition, a window-based framework for quantum image processing applications is proposed. The generated convolution and pooling circuits are simulated on the IBM QISKIT simulator in parallel thanks to the proposed framework. The obtained results are verified by the expected results. Due to the limitations of quantum simulators and computers in the NISQ era, the used grayscale images are resized to 8x8 and the resolution of the images is reduced to 3 qubits. With developing the quantum technologies, the proposed approach can be applied for bigger and higher resolution images. Although the proposed method causes more qubit usage and circuit depth compared to variational convolutional circuits, the results they produce are exactly the same as the classical convolution process.

Traitement du signal•Apr 30, 2022•7 citations

Parameter Efficiency of Variational Quantum Circuits in Image Classification: The Role of Circuit Depth

Pranauv Muthuraman

The practical value of quantum machine learning must be derived from efficiency rather than scale, as current NISQ processors support only small, shallow circuits. This paper evaluated whether variational quantum circuits (VQCs) can reduce the trainable parameter count in an image classification scenario while preserving accuracy. Experimentation compared quantum classifier heads to parameter-matched classical heads on an identical set of frozen features drawn from the Fashion-MNIST dataset by a CNN. 9 configurations of a quantum circuit crossed 4, 6, and 8 qubits with 1, 2, and 4 entangling layers, each matched to a multilayer perceptron with an approximately equal parameter count. The linear probes served as a floor baseline for all 105 runs across 5 random seed values. 7 out of 9 quantum-based configurations met the mean test accuracy of no more than 1 percentage point below its matched classical head, enforced by the pre-specified criterion. The 2 failures were single-layer circuits, with each falling roughly 8 points below its matched classical head and 12 points below the circuit-free linear probe; in total, 6 configs with 2+ layers passed, with the smallest at 74 trainable parameters. The general trend noticed was that accuracy increased progressively with depth. The 4-layer circuits exceeded the linear probe at every qubit count and produced the highest accuracy at 6 and 8 qubits. The simulation ran noiselessly; VQCs preserved accuracy at the matched parameter budget when depth was given, showcasing depth rather than qubit count gating performance.

•Aug 15, 2026•0 citations

A Quantum-Classical Hybrid Classifier Using Multi-Encoding Method for Images

Níyazí Furkan Bar, Hasan Yetış, Mehmet Karaköse

Image data grows in volume and size more quickly than classical processing power. Thanks to its entanglement and super-position qualities, quantum computing, which is based on quantum physics, has a lot of potential for speed and processing capacity. For high power challenges, it is therefore highly common to try to utilize quantum computing units rather than classical computing units. In this study, a hybrid quantum-classical approach was proposed for utilizing quantum computers’ advantages in image classification. This hybrid technique uses a variational quantum circuit (VQC) on the quantum computer side. To overcome the qubit restriction in the VQC, multiple amplitude encoding was used as the data encoding method. In the classical computer part of the proposed approach, the preprocessing of the image, the convolution operation, and the optimization of the parameters of the single-qubit rotation gates in the VQC were performed. The proposed approach was trained and tested on two different data sets. The accuracy rates acquired in 2-layers and 4-layers VQCs within the data sets were evaluated in the test results. The proposed approach was evaluated against studies that were similar in the literature. Compared to similar studies, it was observed that it is more successful in terms of the number of parameters used and quantum cost. As a result, the effectiveness of the proposed approach was verified.

•Feb 15, 2023•11 citations

Training Variational Quantum Circuits Using Particle Swarm Optimization

Marco Mordacci, Michele Amoretti

In this work, the Particle Swarm Optimization (PSO) algorithm has been used to train various Variational Quantum Circuits (VQCs). This approach is motivated by the fact that commonly used gradient-based optimization methods can suffer from the barren plateaus problem. PSO is a stochastic optimization technique inspired by the collective behavior of a swarm of birds. The dimension of the swarm, the number of iterations of the algorithm, and the number of trainable parameters can be set. In this study, PSO has been used to train the entire structure of VQCs, allowing it to select which quantum gates to apply, the target qubits, and the rotation angle, in case a rotation is chosen. The algorithm is restricted to choosing from four types of gates: Rx, Ry, Rz, and cNOT. The proposed optimization approach has been tested on various datasets of the MedMNIST, which is a collection of biomedical image datasets designed for image classification tasks. Performance has been compared with the results achieved by classical stochastic gradient descent applied to a predefined VQC. The results show that the PSO can achieve comparable or even better classification accuracy across multiple datasets, despite the PSO using a lower number of quantum gates than the VQC used with gradient descent optimization.

arXiv:2509.15726•IEEE International Conference on Quantum Computing and Engineering (QCE)•Aug 30, 2025•0 citations

Hybrid quantum-classical-quantum convolutional neural networks

Changzhou Long, Mengyuan Huang, Xiucai Ye +2 more

Deep learning has achieved significant success in pattern recognition, with convolutional neural networks (CNNs) serving as a foundational architecture for extracting spatial features from images. Quantum computing provides an alternative computational framework, a hybrid quantum-classical convolutional neural networks (QCCNNs) leverage high-dimensional Hilbert spaces and entanglement to surpass classical CNNs in image classification accuracy under comparable architectures. Despite performance improvements, QCCNNs typically use fixed quantum layers without incorporating trainable quantum parameters. This limits their ability to capture non-linear quantum representations and separates the model from the potential advantages of expressive quantum learning. In this work, we present a hybrid quantum-classical-quantum convolutional neural network (QCQ-CNN) that incorporates a quantum convolutional filter, a shallow classical CNN, and a trainable variational quantum classifier. This architecture aims to enhance the expressivity of decision boundaries in image classification tasks by introducing tunable quantum parameters into the end-to-end learning process. Through a series of small-sample experiments on MNIST, F-MNIST, and MRI tumor datasets, QCQ-CNN demonstrates competitive accuracy and convergence behavior compared to classical and hybrid baselines. We further analyze the effect of ansatz depth and find that moderate-depth quantum circuits can improve learning stability without introducing excessive complexity. Additionally, simulations incorporating depolarizing noise and finite sampling shots suggest that QCQ-CNN maintains a certain degree of robustness under realistic quantum noise conditions. While our results are currently limited to simulations with small-scale quantum circuits, the proposed approach offers a potentially promising direction for hybrid quantum learning in near-term applications.

Scientific Reports•Aug 28, 2025•93 citations

Variational quantum circuits for visual inspection in intelligent manufacturing: A critical review through a parameter-accounting framework

Tarina Jayant, Rakesh Kumar, Shankar Singh

Automated visual inspection underpins quality assurance in intelligent manufacturing. However, the convolutional and transformer models used for this purpose can be costly to deploy at the network edge, where latency and energy budgets are tight. Variational quantum circuits (VQCs) are often advanced as a low-parameter alternative, the reasoning being that n qubits carry a state space of size 2ⁿ, so that comparatively few trainable angles might still describe an intricate decision surface. This selective narrative review asks whether that reasoning survives once resources are tallied from sensor input through to decision. A framework proposed that separates task-specific trainable parameters, stored non-trainable parameters, and fitted quantities, preprocessing compression, and quantum encoding reach, and apply it to representative hybrid pipelines. Three findings emerge. First, claimed quantum gains tend to arise in studies where the classical baseline differs from the quantum pipeline in parameter count, preprocessing applied, or the amount of tuning each received. A prominent controlled benchmark for small binary classification tasks generally favors classical models, although direct extrapolation of that result to industrial vision remains unproven. Second, the selected examples show few trainable angles within the circuit, but the representational burden is largely shifted onto classical preprocessing or frozen backbones. Third, scalability is constrained by both encoding reach and state preparation: a standard video clip can contain nearly 5 × 106 values, and generic amplitude loading may require millions of operations. These constraints are particularly relevant to video and sequential-image process monitoring. Six reporting requirements are proposed to make future comparisons reproducible.

International Journal of Research in Engineering and Innovation•Jan 1, 2026•0 citations
Abstract Quantum information processing is gaining popularity in the fields of machine learning and image processing because of its advantages. Quantum convolution is an interesting topic in this field, and studies on this topic can be divided into value-based and angle-based methods. Although quantum convolution studies on angle-based or variational quantum circuits (VQCs) is called convolution, the circuits work differently from classical convolution. In this study, contrary to the literature, the VQC was trained to imitate classical convolution. The differential evolution algorithm (DEA) was used to optimize the VQCs. The proposed method requires as many qubits as the filter size (N× N). The generated circuits contain N× N× 4 quantum gates and N× N × 3 trainable parameters. The generated circuits were tested in Python environment using Cirq simulator. The Cifar10 and MNIST datasets are used as examples. For 2 × 2 filters with different weights, the convolution was successfully modeled with a mean squared error of less than 0.001. In general, the proposed method imitates classic convolution within ± 5 % tolerance. In conclusion, VQCs that imitate classical convolution with fewer qubits and quantum gates than value-based methods were obtained.
The resource need for deep learning and quantum computers' high computing power potential encourage collaboration between the two fields. Today, variational quantum circuits are used to perform the convolution operation with quantum computing. However, the results produced by variational circuits do not show a direct resemblance to the classical convolution operation. Because classical data is encoded into quantum data with their exact values in value-encoded methods, in contrast to variational quantum circuits, arithmetical operations can be applied with high accuracy. In this study, value-encoded quantum circuits for convolution and pooling operations are proposed to apply deep learning in quantum computers in a traditional and proven way. To construct the convolution and pooling operations, some modules such as addition, multiplication, division, and comparison are created. In addition, a window-based framework for quantum image processing applications is proposed. The generated convolution and pooling circuits are simulated on the IBM QISKIT simulator in parallel thanks to the proposed framework. The obtained results are verified by the expected results. Due to the limitations of quantum simulators and computers in the NISQ era, the used grayscale images are resized to 8x8 and the resolution of the images is reduced to 3 qubits. With developing the quantum technologies, the proposed approach can be applied for bigger and higher resolution images. Although the proposed method causes more qubit usage and circuit depth compared to variational convolutional circuits, the results they produce are exactly the same as the classical convolution process.
The practical value of quantum machine learning must be derived from efficiency rather than scale, as current NISQ processors support only small, shallow circuits. This paper evaluated whether variational quantum circuits (VQCs) can reduce the trainable parameter count in an image classification scenario while preserving accuracy. Experimentation compared quantum classifier heads to parameter-matched classical heads on an identical set of frozen features drawn from the Fashion-MNIST dataset by a CNN. 9 configurations of a quantum circuit crossed 4, 6, and 8 qubits with 1, 2, and 4 entangling layers, each matched to a multilayer perceptron with an approximately equal parameter count. The linear probes served as a floor baseline for all 105 runs across 5 random seed values. 7 out of 9 quantum-based configurations met the mean test accuracy of no more than 1 percentage point below its matched classical head, enforced by the pre-specified criterion. The 2 failures were single-layer circuits, with each falling roughly 8 points below its matched classical head and 12 points below the circuit-free linear probe; in total, 6 configs with 2+ layers passed, with the smallest at 74 trainable parameters. The general trend noticed was that accuracy increased progressively with depth. The 4-layer circuits exceeded the linear probe at every qubit count and produced the highest accuracy at 6 and 8 qubits. The simulation ran noiselessly; VQCs preserved accuracy at the matched parameter budget when depth was given, showcasing depth rather than qubit count gating performance.
Image data grows in volume and size more quickly than classical processing power. Thanks to its entanglement and super-position qualities, quantum computing, which is based on quantum physics, has a lot of potential for speed and processing capacity. For high power challenges, it is therefore highly common to try to utilize quantum computing units rather than classical computing units. In this study, a hybrid quantum-classical approach was proposed for utilizing quantum computers’ advantages in image classification. This hybrid technique uses a variational quantum circuit (VQC) on the quantum computer side. To overcome the qubit restriction in the VQC, multiple amplitude encoding was used as the data encoding method. In the classical computer part of the proposed approach, the preprocessing of the image, the convolution operation, and the optimization of the parameters of the single-qubit rotation gates in the VQC were performed. The proposed approach was trained and tested on two different data sets. The accuracy rates acquired in 2-layers and 4-layers VQCs within the data sets were evaluated in the test results. The proposed approach was evaluated against studies that were similar in the literature. Compared to similar studies, it was observed that it is more successful in terms of the number of parameters used and quantum cost. As a result, the effectiveness of the proposed approach was verified.
In this work, the Particle Swarm Optimization (PSO) algorithm has been used to train various Variational Quantum Circuits (VQCs). This approach is motivated by the fact that commonly used gradient-based optimization methods can suffer from the barren plateaus problem. PSO is a stochastic optimization technique inspired by the collective behavior of a swarm of birds. The dimension of the swarm, the number of iterations of the algorithm, and the number of trainable parameters can be set. In this study, PSO has been used to train the entire structure of VQCs, allowing it to select which quantum gates to apply, the target qubits, and the rotation angle, in case a rotation is chosen. The algorithm is restricted to choosing from four types of gates: Rx, Ry, Rz, and cNOT. The proposed optimization approach has been tested on various datasets of the MedMNIST, which is a collection of biomedical image datasets designed for image classification tasks. Performance has been compared with the results achieved by classical stochastic gradient descent applied to a predefined VQC. The results show that the PSO can achieve comparable or even better classification accuracy across multiple datasets, despite the PSO using a lower number of quantum gates than the VQC used with gradient descent optimization.
Deep learning has achieved significant success in pattern recognition, with convolutional neural networks (CNNs) serving as a foundational architecture for extracting spatial features from images. Quantum computing provides an alternative computational framework, a hybrid quantum-classical convolutional neural networks (QCCNNs) leverage high-dimensional Hilbert spaces and entanglement to surpass classical CNNs in image classification accuracy under comparable architectures. Despite performance improvements, QCCNNs typically use fixed quantum layers without incorporating trainable quantum parameters. This limits their ability to capture non-linear quantum representations and separates the model from the potential advantages of expressive quantum learning. In this work, we present a hybrid quantum-classical-quantum convolutional neural network (QCQ-CNN) that incorporates a quantum convolutional filter, a shallow classical CNN, and a trainable variational quantum classifier. This architecture aims to enhance the expressivity of decision boundaries in image classification tasks by introducing tunable quantum parameters into the end-to-end learning process. Through a series of small-sample experiments on MNIST, F-MNIST, and MRI tumor datasets, QCQ-CNN demonstrates competitive accuracy and convergence behavior compared to classical and hybrid baselines. We further analyze the effect of ansatz depth and find that moderate-depth quantum circuits can improve learning stability without introducing excessive complexity. Additionally, simulations incorporating depolarizing noise and finite sampling shots suggest that QCQ-CNN maintains a certain degree of robustness under realistic quantum noise conditions. While our results are currently limited to simulations with small-scale quantum circuits, the proposed approach offers a potentially promising direction for hybrid quantum learning in near-term applications.
Automated visual inspection underpins quality assurance in intelligent manufacturing. However, the convolutional and transformer models used for this purpose can be costly to deploy at the network edge, where latency and energy budgets are tight. Variational quantum circuits (VQCs) are often advanced as a low-parameter alternative, the reasoning being that n qubits carry a state space of size 2ⁿ, so that comparatively few trainable angles might still describe an intricate decision surface. This selective narrative review asks whether that reasoning survives once resources are tallied from sensor input through to decision. A framework proposed that separates task-specific trainable parameters, stored non-trainable parameters, and fitted quantities, preprocessing compression, and quantum encoding reach, and apply it to representative hybrid pipelines. Three findings emerge. First, claimed quantum gains tend to arise in studies where the classical baseline differs from the quantum pipeline in parameter count, preprocessing applied, or the amount of tuning each received. A prominent controlled benchmark for small binary classification tasks generally favors classical models, although direct extrapolation of that result to industrial vision remains unproven. Second, the selected examples show few trainable angles within the circuit, but the representational burden is largely shifted onto classical preprocessing or frozen backbones. Third, scalability is constrained by both encoding reach and state preparation: a standard video clip can contain nearly 5 × 106 values, and generic amplitude loading may require millions of operations. These constraints are particularly relevant to video and sequential-image process monitoring. Six reporting requirements are proposed to make future comparisons reproducible.