Quantum Patch-Based Autoencoder for Anomaly Segmentation

arXiv:2404.17613v1 Announce Type: cross
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 …

abstract algorithms anomaly arxiv autoencoder autoencoders computers cs.lg domains fundamental identify machine machine learning machine learning algorithms possibility quant-ph quantum quantum computers sample segmentation tasks type unsupervised