Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamics

by   Minkyung Kim, et al.
KAIST 수리과학과

One-class classification has been a prevailing method in building deep anomaly detection models under the assumption that a dataset consisting of normal samples is available. In practice, however, abnormal samples are often mixed in a training dataset, and they detrimentally affect the training of deep models, which limits their applicability. For robust normality learning of deep practical models, we propose an unsupervised deep one-class classification that learns normality from pseudo-labeled normal samples, i.e., outlier detection in single cluster scenarios. To this end, we propose a pseudo-labeling method by an adaptive threshold selected by ranking-based training dynamics. The experiments on 10 anomaly detection benchmarks show that our method effectively improves performance on anomaly detection by sizable margins.


page 1

page 2

page 3

page 4


Self-Trained One-class Classification for Unsupervised Anomaly Detection

Anomaly detection (AD), separating anomalies from normal data, has vario...

Active anomaly detection based on deep one-class classification

Active learning has been utilized as an efficient tool in building anoma...

An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination

Most deep anomaly detection models are based on learning normality from ...

Health Monitoring of Industrial machines using Scene-Aware Threshold Selection

This paper presents an autoencoder based unsupervised approach to identi...

Normalizing flows for deep anomaly detection

Anomaly detection for complex data is a challenging task from the perspe...

Few-shot Deep Representation Learning based on Information Bottleneck Principle

In a standard anomaly detection problem, a detection model is trained in...

Unsupervised Learning of the Set of Local Maxima

This paper describes a new form of unsupervised learning, whose input is...

Please sign up or login with your details

Forgot password? Click here to reset