Constricting Normal Latent Space for Anomaly Detection with Normal-only Training Data

arXiv:2403.16270v1 Announce Type: new
Abstract: In order to devise an anomaly detection model using only normal training data, an autoencoder (AE) is typically trained to reconstruct the data. As a result, the AE can extract normal representations in its latent space. During test time, since AE is not trained using real anomalies, it is expected to poorly reconstruct the anomalous data. However, several researchers have observed that it is not the case. In this work, we propose to limit the …

abstract anomaly anomaly detection arxiv autoencoder cs.cv data detection extract normal space test training training data type