Quantum Patch-Based Autoencoder for Anomaly Segmentation

TL;DR

This paper introduces a novel quantum autoencoder model for image anomaly segmentation that leverages quantum computing to efficiently identify irregularities without reconstructing entire images.

Contribution

It presents the first application of a patch-based quantum autoencoder for anomaly segmentation, with parameters scaling logarithmically with patch size, and compares its performance to classical methods.

Findings

Quantum autoencoder effectively detects anomalies in images.

Parameter scaling is logarithmic with patch size, improving efficiency.

Performance comparison shows competitive results against classical autoencoders.

Abstract

Quantum Machine Learning investigates the possibility of quantum computers enhancing Machine Learning algorithms. Anomaly segmentation is a fundamental task in various domains to identify irregularities at sample level and can be addressed with both supervised and unsupervised methods. Autoencoders are commonly used in unsupervised tasks, where models are trained to reconstruct normal instances efficiently, allowing anomaly identification through high reconstruction errors. While quantum autoencoders have been proposed in the literature, their application to anomaly segmentation tasks remains unexplored. In this paper, we introduce a patch-based quantum autoencoder (QPB-AE) for image anomaly segmentation, with a number of parameters scaling logarithmically with patch size. QPB-AE reconstructs the quantum state of the embedded input patches, computing an anomaly map directly from measurement through a SWAP test without reconstructing the input image. We evaluate its performance across multiple datasets and parameter configurations and compare it against a classical counterpart.