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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings / IEEE International Conference on Computer Vision s. 1705 - 1714
Hlavní autoři: Gong, Dong, Liu, Lingqiao, Le, Vuong, Saha, Budhaditya, Mansour, Moussa Reda, Venkatesh, Svetha, Van Den Hengel, Anton
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.10.2019
Témata:
Anomaly detection
Decoding
Encoding
Image reconstruction
Memory modules
Micromechanical devices
Training
ISSN:2380-7504
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
ISSN:2380-7504
DOI:10.1109/ICCV.2019.00179