Transfer Learning Based Hybrid Quantum Neural Network Model for Surface Anomaly Detection

TL;DR

This paper introduces a quantum transfer learning hybrid model for surface anomaly detection that significantly reduces model parameters and training time while maintaining or improving performance, addressing resource and flexibility issues.

Contribution

The paper proposes a novel quantum transfer learning approach that reduces classical model parameters by up to 90% without performance loss, enhancing efficiency and adaptability.

Findings

Reduced parameters by up to 90% without performance loss

Improved model flexibility and response speed

Effective surface anomaly detection with hybrid quantum-classical models

Abstract

The rapid increase in the volume of data increased the size and complexity of the deep learning models. These models are now more resource-intensive and time-consuming for training than ever. This paper presents a quantum transfer learning (QTL) based approach to significantly reduce the number of parameters of the classical models without compromising their performance, sometimes even improving it. Reducing the number of parameters reduces overfitting problems and training time and increases the models' flexibility and speed of response. For illustration, we have selected a surface anomaly detection problem to show that we can replace the resource-intensive and less flexible anomaly detection system (ADS) with a quantum transfer learning-based hybrid model to address the frequent emergence of new anomalies better. We showed that we could reduce the total number of trainable parameters up to 90% of the initial model without any drop in performance.