Qubit-efficient Variational Quantum Algorithms for Image Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Venkatesh, Supreeth Mysore, Macaluso, Antonio, Nuske, Marlon, Klusch, Matthias, Dengel, Andreas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929688405868544
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 Quantum computing is expected to transform a range of computational tasks beyond the reach of classical algorithms. In this work, we examine the application of variational quantum algorithms (VQAs) for unsupervised image segmentation to partition images into separate semantic regions. Specifically, we formulate the task as a graph cut optimization problem and employ two established qubit-efficient VQAs, which we refer to as Parametric Gate Encoding (PGE) and Ancilla Basis Encoding (ABE), to find the optimal segmentation mask. In addition, we propose Adaptive Cost Encoding (ACE), a new approach that leverages the same circuit architecture as ABE but adopts a problem-dependent cost function. We benchmark PGE, ABE and ACE on synthetically generated images, focusing on quality and trainability. ACE shows consistently faster convergence in training the parameterized quantum circuits in comparison to PGE and ABE. Furthermore, we provide a theoretical analysis of the scalability of these approaches against the Quantum Approximate Optimization Algorithm (QAOA), showing a significant cutback in the quantum resources, especially in the number of qubits that logarithmically depends on the number of pixels. The results validate the strengths of ACE, while concurrently highlighting its inherent limitations and challenges. This paves way for further research in quantum-enhanced computer vision.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14405
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Qubit-efficient Variational Quantum Algorithms for Image Segmentation
Venkatesh, Supreeth Mysore
Macaluso, Antonio
Nuske, Marlon
Klusch, Matthias
Dengel, Andreas
Computer Vision and Pattern Recognition
Image and Video Processing
Quantum Physics
Quantum computing is expected to transform a range of computational tasks beyond the reach of classical algorithms. In this work, we examine the application of variational quantum algorithms (VQAs) for unsupervised image segmentation to partition images into separate semantic regions. Specifically, we formulate the task as a graph cut optimization problem and employ two established qubit-efficient VQAs, which we refer to as Parametric Gate Encoding (PGE) and Ancilla Basis Encoding (ABE), to find the optimal segmentation mask. In addition, we propose Adaptive Cost Encoding (ACE), a new approach that leverages the same circuit architecture as ABE but adopts a problem-dependent cost function. We benchmark PGE, ABE and ACE on synthetically generated images, focusing on quality and trainability. ACE shows consistently faster convergence in training the parameterized quantum circuits in comparison to PGE and ABE. Furthermore, we provide a theoretical analysis of the scalability of these approaches against the Quantum Approximate Optimization Algorithm (QAOA), showing a significant cutback in the quantum resources, especially in the number of qubits that logarithmically depends on the number of pixels. The results validate the strengths of ACE, while concurrently highlighting its inherent limitations and challenges. This paves way for further research in quantum-enhanced computer vision.
title Qubit-efficient Variational Quantum Algorithms for Image Segmentation
topic Computer Vision and Pattern Recognition
Image and Video Processing
Quantum Physics
url https://arxiv.org/abs/2405.14405