Exploiting Autoencoder's Weakness to Generate Pseudo Anomalies

arXiv:2405.05886v1 Announce Type: new
Abstract: Due to the rare occurrence of anomalous events, a typical approach to anomaly detection is to train an autoencoder (AE) with normal data only so that it learns the patterns or representations of the normal training data. At test time, the trained AE is expected to well reconstruct normal but to poorly reconstruct anomalous data. However, contrary to the expectation, anomalous data is often well reconstructed as well. In order to further separate the reconstruction …

abstract anomaly anomaly detection arxiv autoencoder cs.cv cs.lg data detection events generate normal patterns test train training training data type