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:2405.19722 · IEEE International Conference on Quantum Computing and Engineering (QCE)

QClusformer: A Quantum Transformer-based Framework for Unsupervised Visual Clustering

Xuan-Bac Nguyen, Hoang-Quan Nguyen, Samuel Yen-Chi Chen, Samee U. Khan, Hugh Churchill, Khoa Luu

Published Sep 15, 2024• 18 citations
arXivHTMLPDF

Abstract

Unsupervised vision clustering, a cornerstone in computer vision, has been studied for decades, yielding signif-icant outcomes across numerous vision tasks. However, these algorithms involve substantial computational demands when confronted with vast amounts of unlabeled data. Conversely, quantum computing holds promise in expediting unsupervised algorithms when handling large-scale databases. In this study, we introduce QClusformer, a pioneering Transformer-based frame-work leveraging quantum machines to tackle unsupervised vision clustering challenges. Specifically, we design the Transformer architecture, including the self-attention module and transformer blocks, from a quantum perspective to enable execution on quan-tum hardware. In addition, we present QClusformer, a variant based on the Transformer architecture, tailored for unsupervised vision clustering tasks. By integrating these elements into an end-to-end framework, QClusformer consistently outperforms previous methods running on classical computers. Empirical evaluations across diverse benchmarks, including MS-Celeb-1M and DeepFashion, underscore the superior performance of QClusformer compared to state-of-the-art methods.

DOI
10.1109/qce60285.2024.10304

Related papers

Measurements With A Quantum Vision Transformer: A Naive Approach

Dominic Pasquali, Michele Grossi, Sofia Vallecorsa

In mainstream machine learning, transformers are gaining widespread usage. As Vision Transformers rise in popularity in computer vision, they now aim to tackle a wide variety of machine learning applications. In particular, transformers for High Energy Physics (HEP) experiments continue to be investigated for tasks including jet tagging, particle reconstruction, and pile-up mitigation. An improved Quantum Vision Transformer (QViT) with a quantum-enhanced self-attention mechanism is introduced and discussed. A shallow circuit is proposed for each component of self-attention to leverage current Noisy Intermediate Scale Quantum (NISQ) devices. Variations of the hybrid architecture/model are explored and analyzed. The results demonstrate a successful proof of concept for the QViT, and establish a competitive performance benchmark for the proposed design and implementation. The findings also provide strong motivation to experiment with different architectures, hyperparameters, and datasets, setting the stage for implementation in HEP environments where transformers are increasingly used in state of the art machine learning solutions.

EPJ Web of Conferences•Jan 1, 2024•4 citations

Quantum Vision Clustering

Xuan-Bac Nguyen, Hugh Churchill, Khoa Luu +1 more

Abstract Unsupervised visual clustering has garnered significant attention recently, aiming to characterize distributions of unlabeled visual images through clustering based on a parameterized appearance approach. Alternatively, clustering algorithms can be viewed as assignment problems where an unlabelled sample needs to be assigned into a specific cluster. This problem can be formulated as Quadratic Unconstrained Binary Optimization that is characterized as NP-hard, yet precisely solvable for small instances on contemporary hardware. Adiabatic quantum computing (AQC) emerges as a promising solution to offer a good speed in solving the NP-hard optimization problems. However, existing clustering approaches face challenges in designing the problems to be solved by the quantum computer. In this study, we present the first clustering formulation tailored for resolution using Adiabatic quantum computing. An Ising model is introduced to represent the quantum mechanical system implemented on AQC. The proposed approach demonstrates high competitiveness compared to state-of-the-art optimization-based methods, even when utilizing off-the-shelf integer programming solvers. Lastly, this work showcases the solvability of the proposed clustering problem on current-generation real quantum computers for small examples and analyzes the properties of the obtained solutions.

arXiv:2309.09907•May 27, 2025•1 citation

Efficient Quantum Algorithms for Data Clustering

Julien Rauch

Data clustering consists of grouping data without prior training, a process known as unsupervised learning. Given the constant growth of database volumes, contemporary computers require significant computational time to perform this partitioning. To effectively address this challenge, quantum computing offers a promising perspective, as it could eventually provide more efficient resources for clustering massive datasets. However, current quantum computers are not yet mature; they are prone to noise, which limits their practical utility. In this context, we have designed a hybrid classical-quantum clustering algorithm tailored for the current Noisy Intermediate-Scale Quantum (NISQ) era. We evaluated this algorithm under various conditions and across different types of datasets, comparing it against several well-known clustering algorithms. Our results demonstrate that, under certain conditions, quantum noise can actually provide an advantage to our algorithm. Furthermore, we worked on deploying this algorithm on actual quantum processors and developed tools to optimize this deployment. Finally, to diversify the quantum architectures used, we extended our research to include neutral-atom quantum computers.

•Oct 8, 2026•0 citations

Quantum Vision Transformers

El Amine Cherrat, Iordanis Kerenidis, Natansh Mathur +3 more

In this work, quantum transformers are designed and analysed in detail by extending the state-of-the-art classical transformer neural network architectures known to be very performant in natural language processing and image analysis. Building upon the previous work, which uses parametrised quantum circuits for data loading and orthogonal neural layers, we introduce three types of quantum transformers for training and inference, including a quantum transformer based on compound matrices, which guarantees a theoretical advantage of the quantum attention mechanism compared to their classical counterpart both in terms of asymptotic run time and the number of model parameters. These quantum architectures can be built using shallow quantum circuits and produce qualitatively different classification models. The three proposed quantum attention layers vary on the spectrum between closely following the classical transformers and exhibiting more quantum characteristics. As building blocks of the quantum transformer, we propose a novel method for loading a matrix as quantum states as well as two new trainable quantum orthogonal layers adaptable to different levels of connectivity and quality of quantum computers. We performed extensive simulations of the quantum transformers on standard medical image datasets that showed competitively, and at times better performance compared to the classical benchmarks, including the best-in-class classical vision transformers. The quantum transformers we trained on these small-scale datasets require fewer parameters compared to standard classical benchmarks. Finally, we implemented our quantum transformers on superconducting quantum computers and obtained encouraging results for up to six qubit experiments.

arXiv:2209.08167•Quantum•Feb 22, 2024•103 citations

Planning, Design, and Execution of a Quantum Incremental Clustering Algorithm System for the Examination of Unsupervised Data

Pornima Niranjane Vaibhav D. Dabhade

The exponential growth of data in various domains has underscored the need for efficient unsupervised learning algorithms to discover hidden patterns and structures within large datasets. Traditional clustering algorithms often face challenges in handling dynamic datasets and require periodic retraining, making them less suitable for real-time applications. In response to these challenges, this research introduces a Quantum Incremental Clustering Algorithm System (QICAS) designed to adapt to evolving datasets and provide timely insights into the underlying structures. The proposed QICAS is based on quantum computing principles, leveraging the unique properties of qubits and quantum superposition to perform clustering tasks more efficiently than classical counterparts. The research focuses on the planning, design, and execution of the QICAS, ensuring a comprehensive understanding of the algorithm's capabilities and performance.

Journal of Electrical Systems•Mar 31, 2024•0 citations

Quantum Architecture Search with Unsupervised Representation Learning

Yize Sun, Zixin Wu, Volker Tresp +1 more

Unsupervised representation learning presents new opportunities for advancing Quantum Architecture Search (QAS) on Noisy Intermediate-Scale Quantum (NISQ) devices. QAS is designed to optimize quantum circuits for Variational Quantum Algorithms (VQAs). Most QAS algorithms tightly couple the search space and search algorithm, typically requiring the evaluation of numerous quantum circuits, resulting in high computational costs and limiting scalability to larger quantum circuits. Predictor-based QAS algorithms mitigate this issue by estimating circuit performance based on structure or embedding. However, these methods often demand time-intensive labeling to optimize gate parameters across many circuits, which is crucial for training accurate predictors. Inspired by the classical neural architecture search algorithm A r c h 2 v e c , we investigate the potential of unsupervised representation learning for QAS without relying on predictors. Our framework decouples unsupervised architecture representation learning from the search process, enabling the learned representations to be applied across various downstream tasks. Additionally, it integrates an improved quantum circuit graph encoding scheme, addressing the limitations of existing representations and enhancing search efficiency. This predictor-free approach removes the need for large labeled datasets. During the search, we employ REINFORCE and Bayesian Optimization to explore the latent representation space and compare their performance against baseline methods. We further validate our approach by executing the best-discovered MaxCut circuits on IBM's ibm_sherbrooke quantum processor, confirming that the architectures retain optimal performance even under real hardware noise. Our results demonstrate that the framework efficiently identifies high-performing quantum circuits with fewer search iterations.

arXiv:2401.11576•Quantum•Feb 3, 2026•6 citations
Unsupervised vision clustering, a cornerstone in computer vision, has been studied for decades, yielding signif-icant outcomes across numerous vision tasks. However, these algorithms involve substantial computational demands when confronted with vast amounts of unlabeled data. Conversely, quantum computing holds promise in expediting unsupervised algorithms when handling large-scale databases. In this study, we introduce QClusformer, a pioneering Transformer-based frame-work leveraging quantum machines to tackle unsupervised vision clustering challenges. Specifically, we design the Transformer architecture, including the self-attention module and transformer blocks, from a quantum perspective to enable execution on quan-tum hardware. In addition, we present QClusformer, a variant based on the Transformer architecture, tailored for unsupervised vision clustering tasks. By integrating these elements into an end-to-end framework, QClusformer consistently outperforms previous methods running on classical computers. Empirical evaluations across diverse benchmarks, including MS-Celeb-1M and DeepFashion, underscore the superior performance of QClusformer compared to state-of-the-art methods.
In mainstream machine learning, transformers are gaining widespread usage. As Vision Transformers rise in popularity in computer vision, they now aim to tackle a wide variety of machine learning applications. In particular, transformers for High Energy Physics (HEP) experiments continue to be investigated for tasks including jet tagging, particle reconstruction, and pile-up mitigation. An improved Quantum Vision Transformer (QViT) with a quantum-enhanced self-attention mechanism is introduced and discussed. A shallow circuit is proposed for each component of self-attention to leverage current Noisy Intermediate Scale Quantum (NISQ) devices. Variations of the hybrid architecture/model are explored and analyzed. The results demonstrate a successful proof of concept for the QViT, and establish a competitive performance benchmark for the proposed design and implementation. The findings also provide strong motivation to experiment with different architectures, hyperparameters, and datasets, setting the stage for implementation in HEP environments where transformers are increasingly used in state of the art machine learning solutions.
Abstract Unsupervised visual clustering has garnered significant attention recently, aiming to characterize distributions of unlabeled visual images through clustering based on a parameterized appearance approach. Alternatively, clustering algorithms can be viewed as assignment problems where an unlabelled sample needs to be assigned into a specific cluster. This problem can be formulated as Quadratic Unconstrained Binary Optimization that is characterized as NP-hard, yet precisely solvable for small instances on contemporary hardware. Adiabatic quantum computing (AQC) emerges as a promising solution to offer a good speed in solving the NP-hard optimization problems. However, existing clustering approaches face challenges in designing the problems to be solved by the quantum computer. In this study, we present the first clustering formulation tailored for resolution using Adiabatic quantum computing. An Ising model is introduced to represent the quantum mechanical system implemented on AQC. The proposed approach demonstrates high competitiveness compared to state-of-the-art optimization-based methods, even when utilizing off-the-shelf integer programming solvers. Lastly, this work showcases the solvability of the proposed clustering problem on current-generation real quantum computers for small examples and analyzes the properties of the obtained solutions.
Data clustering consists of grouping data without prior training, a process known as unsupervised learning. Given the constant growth of database volumes, contemporary computers require significant computational time to perform this partitioning. To effectively address this challenge, quantum computing offers a promising perspective, as it could eventually provide more efficient resources for clustering massive datasets. However, current quantum computers are not yet mature; they are prone to noise, which limits their practical utility. In this context, we have designed a hybrid classical-quantum clustering algorithm tailored for the current Noisy Intermediate-Scale Quantum (NISQ) era. We evaluated this algorithm under various conditions and across different types of datasets, comparing it against several well-known clustering algorithms. Our results demonstrate that, under certain conditions, quantum noise can actually provide an advantage to our algorithm. Furthermore, we worked on deploying this algorithm on actual quantum processors and developed tools to optimize this deployment. Finally, to diversify the quantum architectures used, we extended our research to include neutral-atom quantum computers.
In this work, quantum transformers are designed and analysed in detail by extending the state-of-the-art classical transformer neural network architectures known to be very performant in natural language processing and image analysis. Building upon the previous work, which uses parametrised quantum circuits for data loading and orthogonal neural layers, we introduce three types of quantum transformers for training and inference, including a quantum transformer based on compound matrices, which guarantees a theoretical advantage of the quantum attention mechanism compared to their classical counterpart both in terms of asymptotic run time and the number of model parameters. These quantum architectures can be built using shallow quantum circuits and produce qualitatively different classification models. The three proposed quantum attention layers vary on the spectrum between closely following the classical transformers and exhibiting more quantum characteristics. As building blocks of the quantum transformer, we propose a novel method for loading a matrix as quantum states as well as two new trainable quantum orthogonal layers adaptable to different levels of connectivity and quality of quantum computers. We performed extensive simulations of the quantum transformers on standard medical image datasets that showed competitively, and at times better performance compared to the classical benchmarks, including the best-in-class classical vision transformers. The quantum transformers we trained on these small-scale datasets require fewer parameters compared to standard classical benchmarks. Finally, we implemented our quantum transformers on superconducting quantum computers and obtained encouraging results for up to six qubit experiments.
The exponential growth of data in various domains has underscored the need for efficient unsupervised learning algorithms to discover hidden patterns and structures within large datasets. Traditional clustering algorithms often face challenges in handling dynamic datasets and require periodic retraining, making them less suitable for real-time applications. In response to these challenges, this research introduces a Quantum Incremental Clustering Algorithm System (QICAS) designed to adapt to evolving datasets and provide timely insights into the underlying structures. The proposed QICAS is based on quantum computing principles, leveraging the unique properties of qubits and quantum superposition to perform clustering tasks more efficiently than classical counterparts. The research focuses on the planning, design, and execution of the QICAS, ensuring a comprehensive understanding of the algorithm's capabilities and performance.
Unsupervised representation learning presents new opportunities for advancing Quantum Architecture Search (QAS) on Noisy Intermediate-Scale Quantum (NISQ) devices. QAS is designed to optimize quantum circuits for Variational Quantum Algorithms (VQAs). Most QAS algorithms tightly couple the search space and search algorithm, typically requiring the evaluation of numerous quantum circuits, resulting in high computational costs and limiting scalability to larger quantum circuits. Predictor-based QAS algorithms mitigate this issue by estimating circuit performance based on structure or embedding. However, these methods often demand time-intensive labeling to optimize gate parameters across many circuits, which is crucial for training accurate predictors. Inspired by the classical neural architecture search algorithm A r c h 2 v e c , we investigate the potential of unsupervised representation learning for QAS without relying on predictors. Our framework decouples unsupervised architecture representation learning from the search process, enabling the learned representations to be applied across various downstream tasks. Additionally, it integrates an improved quantum circuit graph encoding scheme, addressing the limitations of existing representations and enhancing search efficiency. This predictor-free approach removes the need for large labeled datasets. During the search, we employ REINFORCE and Bayesian Optimization to explore the latent representation space and compare their performance against baseline methods. We further validate our approach by executing the best-discovered MaxCut circuits on IBM's ibm_sherbrooke quantum processor, confirming that the architectures retain optimal performance even under real hardware noise. Our results demonstrate that the framework efficiently identifies high-performing quantum circuits with fewer search iterations.