Deep Multiple-sphere Support Vector Data Description Based on Variational Autoencoder with Mixture-of-Gaussians Prior

With the continuous increase of data dimension and scale, anomaly detection methods based on deep learning have achieved excellent detection performance, among which deep support vector data description（Deep SVDD） has been widely used.However, it is necessary to impose constraints on various paramet...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Ji suan ji ke xue Jg. 51; H. 6; S. 135 - 143
Hauptverfasser: Wu, Huinan, Xing, Hongjie, Li, Gang
Format: Journal Article
Sprache:Chinesisch
Veröffentlicht: Chongqing Guojia Kexue Jishu Bu 01.06.2024
Editorial office of Computer Science
Schlagworte:
Anomalies
Deep learning
deep support vector data description|mixture-of-gaussians prior|variational autoencoder|anomaly detection|hypersphere collapse
Hyperspheres
Machine learning
Mapping
Mixtures
Parameters
ISSN:1002-137X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:With the continuous increase of data dimension and scale, anomaly detection methods based on deep learning have achieved excellent detection performance, among which deep support vector data description（Deep SVDD） has been widely used.However, it is necessary to impose constraints on various parameters of the mapping network in Deep SVDD to alleviate the hypersphere collapse problem.In order to further improve the feature learning ability of the mapping network in Deep SVDD and solve the hypersphere collapse problem, deep multiple-sphere support vector data description based on variational autoencoder with mixture-of-gaussians prior（DMSVDD-VAE-MoG） is proposed.First, the network parameters and multiple hypersphere centers are initialized by pre-training.Second, the latent features of the training data are obtained by mapping network.The VAE loss, the average radius of multiple hyperspheres together with the average distance between the latent features and their corres-ponding hypersphere centers are jointly o
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1002-137X
DOI:10.11896/jsjkx.230300194