Q-Seg: Quantum Annealing-Based Unsupervised Image Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Venkatesh, Supreeth Mysore, Macaluso, Antonio, Nuske, Marlon, Klusch, Matthias, Dengel, Andreas
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910589506289664
author Venkatesh, Supreeth Mysore
Macaluso, Antonio
Nuske, Marlon
Klusch, Matthias
Dengel, Andreas
author_facet Venkatesh, Supreeth Mysore
Macaluso, Antonio
Nuske, Marlon
Klusch, Matthias
Dengel, Andreas
contents We present Q-Seg, a novel unsupervised image segmentation method based on quantum annealing, tailored for existing quantum hardware. We formulate the pixel-wise segmentation problem, which assimilates spectral and spatial information of the image, as a graph-cut optimization task. Our method efficiently leverages the interconnected qubit topology of the D-Wave Advantage device, offering superior scalability over existing quantum approaches and outperforming several tested state-of-the-art classical methods. Empirical evaluations on synthetic datasets have shown that Q-Seg has better runtime performance than the state-of-the-art classical optimizer Gurobi. The method has also been tested on earth observation image segmentation, a critical area with noisy and unreliable annotations. In the era of noisy intermediate-scale quantum, Q-Seg emerges as a reliable contender for real-world applications in comparison to advanced techniques like Segment Anything. Consequently, Q-Seg offers a promising solution using available quantum hardware, especially in situations constrained by limited labeled data and the need for efficient computational runtime.
format Preprint
id arxiv_https___arxiv_org_abs_2311_12912
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Q-Seg: Quantum Annealing-Based Unsupervised Image Segmentation
Venkatesh, Supreeth Mysore
Macaluso, Antonio
Nuske, Marlon
Klusch, Matthias
Dengel, Andreas
Computer Vision and Pattern Recognition
Quantum Physics
We present Q-Seg, a novel unsupervised image segmentation method based on quantum annealing, tailored for existing quantum hardware. We formulate the pixel-wise segmentation problem, which assimilates spectral and spatial information of the image, as a graph-cut optimization task. Our method efficiently leverages the interconnected qubit topology of the D-Wave Advantage device, offering superior scalability over existing quantum approaches and outperforming several tested state-of-the-art classical methods. Empirical evaluations on synthetic datasets have shown that Q-Seg has better runtime performance than the state-of-the-art classical optimizer Gurobi. The method has also been tested on earth observation image segmentation, a critical area with noisy and unreliable annotations. In the era of noisy intermediate-scale quantum, Q-Seg emerges as a reliable contender for real-world applications in comparison to advanced techniques like Segment Anything. Consequently, Q-Seg offers a promising solution using available quantum hardware, especially in situations constrained by limited labeled data and the need for efficient computational runtime.
title Q-Seg: Quantum Annealing-Based Unsupervised Image Segmentation
topic Computer Vision and Pattern Recognition
Quantum Physics
url https://arxiv.org/abs/2311.12912