OneFlow: One-class flow for anomaly detection based on a minimal volume region

Abstract

We propose OneFlow - a flow-based one-class classifier for anomaly (outlier) detection that finds a minimal volume bounding region. Contrary to density-based methods, OneFlow is constructed in such a way that its result typically does not depend on the structure of outliers. This is caused by the fact that during training the gradient of the cost function is propagated only over the points located near to the decision boundary (behavior similar to the support vectors in SVM). The combination of flow models and a Bernstein quantile estimator allows OneFlow to find a parametric form of bounding region, which can be useful in various applications including describing shapes from 3D point clouds. Experiments show that the proposed model outperforms related methods on real-world anomaly detection problems.

References in corpus (22)

• Auto-Encoding Variational Bayes
• Deep Learning for Anomaly Detection: A Review
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• NICE: Non-linear Independent Components Estimation
• OpenML: networked science in machine learning
• A Unifying Review of Deep and Shallow Anomaly Detection
• Density estimation using Real NVP
• Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
• A Comprehensive Survey of Data Mining-based Fraud Detection Research
• Evaluating Real-time Anomaly Detection Algorithms - the Numenta Anomaly Benchmark
• Deep Anomaly Detection Using Geometric Transformations
• Learning Confidence for Out-of-Distribution Detection in Neural Networks
• Anomaly Detection with Density Estimation
• Deep Structured Energy Based Models for Anomaly Detection
• Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series
• Generative Probabilistic Novelty Detection with Adversarial Autoencoders
• Safe Robot Navigation via Multi-Modal Anomaly Detection
• Anomaly Detection with Score functions based on Nearest Neighbor Graphs
• Unseen Class Discovery in Open-world Classification
• Simple and Effective Prevention of Mode Collapse in Deep One-Class Classification
• Normalizing flows for novelty detection in industrial time series data
• PIDForest: Anomaly Detection via Partial Identification

Cited by in corpus (2)

• DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection
• An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination