Hybrid quantum transfer learning for crack image classification on NISQ hardware

TL;DR

This paper explores a hybrid quantum transfer learning approach for crack detection in images, comparing different quantum hardware platforms to evaluate performance and training efficiency in the NISQ era.

Contribution

It introduces a novel application of quantum transfer learning for crack image classification and provides comparative analysis of quantum hardware performance.

Findings

Quantum transfer learning effectively detects cracks in images.

Performance varies significantly between different quantum hardware.

Training times differ based on hardware and simulation methods.

Abstract

Quantum computers possess the potential to process data using a remarkably reduced number of qubits compared to conventional bits, as per theoretical foundations. However, recent experiments have indicated that the practical feasibility of retrieving an image from its quantum encoded version is currently limited to very small image sizes. Despite this constraint, variational quantum machine learning algorithms can still be employed in the current noisy intermediate scale quantum (NISQ) era. An example is a hybrid quantum machine learning approach for edge detection. In our study, we present an application of quantum transfer learning for detecting cracks in gray value images. We compare the performance and training time of PennyLane's standard qubits with IBM's qasm\_simulator and real backends, offering insights into their execution efficiency.