File(s) under permanent embargo
Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection
conference contribution
posted on 2019-01-01, 00:00 authored by D Gong, L Liu, Vuong Le, Budhaditya Saha, M R Mansour, Svetha VenkateshSvetha Venkatesh, A Van Den Hengel© 2019 IEEE. 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 always hold in practice. It has been observed that sometimes the autoencoder 'generalizes' so well that it can also reconstruct anomalies well, leading to the miss detection of anomalies. To mitigate this drawback for autoencoder based anomaly detector, we propose to augment the autoencoder with a memory module and develop an improved autoencoder called memory-augmented autoencoder, i.e. MemAE. Given an input, MemAE firstly obtains the encoding from the encoder and then uses it as a query to retrieve the most relevant memory items for reconstruction. At the training stage, the memory contents are updated and are encouraged to represent the prototypical elements of the normal data. At the test stage, the learned memory will be fixed, and the reconstruction is obtained from a few selected memory records of the normal data. The reconstruction will thus tend to be close to a normal sample. Thus the reconstructed errors on anomalies will be strengthened for anomaly detection. MemAE is free of assumptions on the data type and thus general to be applied to different tasks. Experiments on various datasets prove the excellent generalization and high effectiveness of the proposed MemAE.
History
Event
Computer Vision. Conference (2019 : Seoul, South Korea)Pagination
1705 - 1714Publisher
IEEELocation
Seoul, South KoreaPlace of publication
Pisctaway, N.J.Publisher DOI
Start date
2019-10-27End date
2019-11-02ISSN
1550-5499ISBN-13
9781728148038Language
engPublication classification
E1 Full written paper - refereedTitle of proceedings
ICCV 2019 : Proceedings of the IEEE International Conference on Computer VisionUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC