Lin Shi

Memory-Augmented Autoencoding with Self-Supervised Learning for Unsupervised Detection of Abnormal Physiological Signals.

MAGE is a novel unsupervised anomaly detection framework that integrates multi head memory gating, self-supervised learning, and adversarial training within a unified convolutional autoencoder architecture that consistently outperforms state-of-the-art baselines in standard within-dataset evaluation settings.