# Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training

arXiv: https://arxiv.org/abs/1905.11034 · HTML: https://mlsanity.com/paper/1905.11034/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2019.

## Built on by (most cited first, 9 of 9)

- [Machine Learning in Aerodynamic Shape Optimization](https://mlsanity.com/paper/2202.07141/) (2022)
- [Self-supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection](https://mlsanity.com/paper/2106.06115/) (2021)
- [ASC-Net : Adversarial-based Selective Network for Unsupervised Anomaly Segmentation](https://mlsanity.com/paper/2103.03664/) (2021)
- [Unsupervised Two-Stage Anomaly Detection](https://mlsanity.com/paper/2103.11671/) (2021)
- [Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination](https://mlsanity.com/paper/2110.14825/) (2021)
- [Image Synthesis as a Pretext for Unsupervised Histopathological Diagnosis](https://mlsanity.com/paper/2104.13797/) (2021)
- [ASC-Net: Unsupervised Medical Anomaly Segmentation Using an Adversarial-based Selective Cutting Network](https://mlsanity.com/paper/2112.09135/) (2021)
- [Scrutinizing Shipment Records To Thwart Illegal Timber Trade](https://mlsanity.com/paper/2208.00493/) (2022)
- [A Generic Machine Learning Framework for Fully-Unsupervised Anomaly Detection with Contaminated Data](https://mlsanity.com/paper/2308.13352/) (2023)

## Abstract (arXiv)

Unsupervised learning of anomaly detection in high-dimensional data, such as images, is a challenging problem recently subject to intense research. Through careful modelling of the data distribution of normal samples, it is possible to detect deviant samples, so called anomalies. Generative Adversarial Networks (GANs) can model the highly complex, high-dimensional data distribution of normal image samples, and have shown to be a suitable approach to the problem. Previously published GAN-based anomaly detection methods often assume that anomaly-free data is available for training. However, this assumption is not valid in most real-life scenarios, a.k.a. in the wild. In this work, we evaluate the effects of anomaly contaminations in the training data on state-of-the-art GAN-based anomaly detection methods. As expected, detection performance deteriorates. To address this performance drop, we propose to add an additional encoder network already at training time and show that joint generator-encoder training stratifies the latent space, mitigating the problem with contaminated data. We show experimentally that the norm of a query image in this stratified latent space becomes a highly significant cue to discriminate anomalies from normal data. The proposed method achieves state-of-the-art performance on CIFAR-10 as well as on a large, previously untested dataset with cell images.