# Deep Variational Semi-Supervised Novelty Detection

arXiv: https://arxiv.org/abs/1911.04971 · HTML: https://mlsanity.com/paper/1911.04971/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Nov 2019.

## Built on by (most cited first, 6 of 6)

- [Training OOD Detectors in their Natural Habitats](https://mlsanity.com/paper/2202.03299/) (2022)
- [ODIM: Outlier Detection via Likelihood of Under-Fitted Generative Models](https://mlsanity.com/paper/2301.04257/) (2023)
- [ISSTAD: Incremental Self-Supervised Learning Based on Transformer for Anomaly Detection and Localization](https://mlsanity.com/paper/2303.17354/) (2023)
- [Anomaly Detection via Multi-Scale Contrasted Memory](https://mlsanity.com/paper/2211.09041/) (2022)
- [AGAD: Adversarial Generative Anomaly Detection](https://mlsanity.com/paper/2304.04211/) (2023)
- [Dual-Mode Deep Anomaly Detection for Medical Manufacturing: Structural Similarity and Feature Distance](https://mlsanity.com/paper/2509.05796/) (2025)

## Abstract (arXiv)

In anomaly detection (AD), one seeks to identify whether a test sample is abnormal, given a data set of normal samples. A recent and promising approach to AD relies on deep generative models, such as variational autoencoders (VAEs), for unsupervised learning of the normal data distribution. In semi-supervised AD (SSAD), the data also includes a small sample of labeled anomalies. In this work, we propose two variational methods for training VAEs for SSAD. The intuitive idea in both methods is to train the encoder to `separate' between latent vectors for normal and outlier data. We show that this idea can be derived from principled probabilistic formulations of the problem, and propose simple and effective algorithms. Our methods can be applied to various data types, as we demonstrate on SSAD datasets ranging from natural images to astronomy and medicine, can be combined with any VAE model architecture, and are naturally compatible with ensembling. When comparing to state-of-the-art SSAD methods that are not specific to particular data types, we obtain marked improvement in outlier detection.