Are generative deep models for novelty detection truly better?

Abstract

Many deep models have been recently proposed for anomaly detection. This paper presents comparison of selected generative deep models and classical anomaly detection methods on an extensive number of non--image benchmark datasets. We provide statistical comparison of the selected models, in many configurations, architectures and hyperparamaters. We arrive to conclusion that performance of the generative models is determined by the process of selection of their hyperparameters. Specifically, performance of the deep generative models deteriorates with decreasing amount of anomalous samples used in hyperparameter selection. In practical scenarios of anomaly detection, none of the deep generative models systematically outperforms the kNN.

arXiv comment7 pages, ODD v5.0 - KDD 2018 workshop

References in corpus (3)

• Adam: A Method for Stochastic Optimization
• Improved Techniques for Training GANs
• Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery

Cited by in corpus (11)

• Deep Learning for Anomaly Detection: A Survey
• Learning and Evaluating Representations for Deep One-class Classification
• Do Deep Generative Models Know What They Don't Know?
• Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality
• Unsupervised Out-of-Distribution Detection with Batch Normalization
• The Hidden Uncertainty in a Neural Networks Activations
• WaveletAE: A Wavelet-enhanced Autoencoder for Wind Turbine Blade Icing Detection
• Anomaly scores for generative models
• Sum-Product-Transform Networks: Exploiting Symmetries using Invertible Transformations
• Exploring Deep Anomaly Detection Methods Based on Capsule Net
• Kullback-Leibler Divergence-Based Out-of-Distribution Detection with Flow-Based Generative Models