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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nguyen, Xuan-Bac, Nguyen, Hoang-Quan, Chen, Samuel Yen-Chi, Khan, Samee U., Churchill, Hugh, Luu, Khoa
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911979998806016
author Nguyen, Xuan-Bac
Nguyen, Hoang-Quan
Chen, Samuel Yen-Chi
Khan, Samee U.
Churchill, Hugh
Luu, Khoa
author_facet Nguyen, Xuan-Bac
Nguyen, Hoang-Quan
Chen, Samuel Yen-Chi
Khan, Samee U.
Churchill, Hugh
Luu, Khoa
contents Unsupervised vision clustering, a cornerstone in computer vision, has been studied for decades, yielding significant 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 framework 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 quantum 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_19722
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle QClusformer: A Quantum Transformer-based Framework for Unsupervised Visual Clustering
Nguyen, Xuan-Bac
Nguyen, Hoang-Quan
Chen, Samuel Yen-Chi
Khan, Samee U.
Churchill, Hugh
Luu, Khoa
Computer Vision and Pattern Recognition
Unsupervised vision clustering, a cornerstone in computer vision, has been studied for decades, yielding significant 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 framework 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 quantum 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.
title QClusformer: A Quantum Transformer-based Framework for Unsupervised Visual Clustering
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.19722