Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection

Deep autoencoder has been extensively used for anomaly detection. Training on the normal data, the autoencoder is expected to produce higher reconstruction error for the abnormal inputs than the normal ones, which is adopted as a criterion for identifying anomalies. However, this assumption does not...

Full description

Bibliographic Details

Published in:	Proceedings / IEEE International Conference on Computer Vision pp. 1705 - 1714
Main Authors:	Gong, Dong, Liu, Lingqiao, Le, Vuong, Saha, Budhaditya, Mansour, Moussa Reda, Venkatesh, Svetha, Van Den Hengel, Anton
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.10.2019
Subjects:	Anomaly detection Decoding Encoding Image reconstruction Memory modules Micromechanical devices Training
ISSN:	2380-7504
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!