# Are generative deep models for novelty detection truly better?

arXiv: https://arxiv.org/abs/1807.05027 · HTML: https://mlsanity.com/paper/1807.05027/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2018.

## Built on by (most cited first, 5 of 5)

- [On the Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributions](https://mlsanity.com/paper/2102.05485/) (2021)
- [Unsupervised Energy-based Out-of-distribution Detection using Stiefel-Restricted Kernel Machine](https://mlsanity.com/paper/2102.08443/) (2021)
- [Deep Unsupervised Anomaly Detection in Brain Imaging: Large-Scale Benchmarking and Bias Analysis](https://mlsanity.com/paper/2512.01534/) (2025)
- [Relaxed Triangle Inequality for Kullback-Leibler Divergence Between Multivariate Gaussian Distributions](https://mlsanity.com/paper/2602.02577/) (2026)
- [Optimal Stability of KL Divergence under Gaussian Perturbations](https://mlsanity.com/paper/2604.11026/) (2026)

## Abstract (arXiv)

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.