Unsupervised Anomaly Detection Using Style Distillation

Unsupervised Anomaly Detection Using Style Distillation

Autoencoders (AEs) have been widely used for unsupervised anomaly detection. They learn from normal samples such that they produce high reconstruction errors for anomalous samples. However, AEs can exhibit the over-detection issue because they imperfectly reconstruct not only anomalous samples but a...

Full description

Bibliographic Details
Main Authors: Hwehee Chung, Jongho Park, Jongsoo Keum, Hongdo Ki, Seokho Kang
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Anomaly detection
style distillation
autoencoder
knowledge distillation
outlier exposure
Online Access:https://ieeexplore.ieee.org/document/9288772/

Internet

https://ieeexplore.ieee.org/document/9288772/

Similar Items