# Robust Anomaly Detection in Images using Adversarial Autoencoders

arXiv: https://arxiv.org/abs/1901.06355 · HTML: https://mlsanity.com/paper/1901.06355/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jan 2019.

## Built on by (most cited first, 30 of 38)

- [Latent Outlier Exposure for Anomaly Detection with Contaminated Data](https://mlsanity.com/paper/2202.08088/) (2022)
- [Self-supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection](https://mlsanity.com/paper/2106.06115/) (2021)
- [A Survey of Graph-based Deep Learning for Anomaly Detection in Distributed Systems](https://mlsanity.com/paper/2206.04149/) (2022)
- [Efficient Out-of-Distribution Detection Using Latent Space of β-VAE for Cyber-Physical Systems](https://mlsanity.com/paper/2108.11800/) (2021)
- [MemStream: Memory-Based Streaming Anomaly Detection](https://mlsanity.com/paper/2106.03837/) (2021)
- [Revisiting Bayesian Autoencoders with MCMC](https://mlsanity.com/paper/2104.05915/) (2021)
- [Autoencoders for Anomaly Detection are Unreliable](https://mlsanity.com/paper/2501.13864/) (2025)
- [Machine Learning in NextG Networks via Generative Adversarial Networks](https://mlsanity.com/paper/2203.04453/) (2022)
- [Out-of-Distribution Detection for Monocular Depth Estimation](https://mlsanity.com/paper/2308.06072/) (2023)
- [StRegA: Unsupervised Anomaly Detection in Brain MRIs using a Compact Context-encoding Variational Autoencoder](https://mlsanity.com/paper/2201.13271/) (2022)
- [Assessing the Quality of the Datasets by Identifying Mislabeled Samples](https://mlsanity.com/paper/2109.05000/) (2021)
- [Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination](https://mlsanity.com/paper/2110.14825/) (2021)
- [Reducing Redundancy in the Bottleneck Representation of the Autoencoders](https://mlsanity.com/paper/2202.04629/) (2022)
- [Reconstruction Error-based Anomaly Detection with Few Outlying Examples](https://mlsanity.com/paper/2305.10464/) (2023)
- [Self-Supervised Iterative Refinement for Anomaly Detection in Industrial Quality Control](https://mlsanity.com/paper/2408.11561/) (2024)
- [An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination](https://mlsanity.com/paper/2309.09436/) (2023)
- [RoCA: Robust Contrastive One-class Time Series Anomaly Detection with Contaminated Data](https://mlsanity.com/paper/2503.18385/) (2025)
- [Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators](https://mlsanity.com/paper/2101.04645/) (2021)
- [Margin-Aware Intra-Class Novelty Identification for Medical Images](https://mlsanity.com/paper/2108.00117/) (2021)
- [R2-AD2: Detecting Anomalies by Analysing the Raw Gradient](https://mlsanity.com/paper/2206.10259/) (2022)
- [Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systems](https://mlsanity.com/paper/2510.21254/) (2025)
- [Attack-Agnostic Adversarial Detection](https://mlsanity.com/paper/2206.00489/) (2022)
- [Representing Camera Response Function by a Single Latent Variable and Fully Connected Neural Network](https://mlsanity.com/paper/2209.03624/) (2022)
- [Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamics](https://mlsanity.com/paper/2302.06048/) (2023)
- [A Robust Autoencoder Ensemble-Based Approach for Anomaly Detection in Text](https://mlsanity.com/paper/2405.13031/) (2024)
- [A 3D Multimodal Feature for Infrastructure Anomaly Detection](https://mlsanity.com/paper/2502.05779/) (2025)
- [OCSVM-Guided Representation Learning for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2507.21164/) (2025)
- [AdeNet: Deep learning architecture that identifies damaged electrical insulators in power lines](https://mlsanity.com/paper/2103.01426/) (2021)
- [A Comparison of Supervised and Unsupervised Deep Learning Methods for Anomaly Detection in Images](https://mlsanity.com/paper/2107.09204/) (2021)
- [The Unreasonable Effectiveness of the Final Batch Normalization Layer](https://mlsanity.com/paper/2109.09016/) (2021)

## Abstract (arXiv)

Reliably detecting anomalies in a given set of images is a task of high practical relevance for visual quality inspection, surveillance, or medical image analysis. Autoencoder neural networks learn to reconstruct normal images, and hence can classify those images as anomalies, where the reconstruction error exceeds some threshold. Here we analyze a fundamental problem of this approach when the training set is contaminated with a small fraction of outliers. We find that continued training of autoencoders inevitably reduces the reconstruction error of outliers, and hence degrades the anomaly detection performance. In order to counteract this effect, an adversarial autoencoder architecture is adapted, which imposes a prior distribution on the latent representation, typically placing anomalies into low likelihood-regions. Utilizing the likelihood model, potential anomalies can be identified and rejected already during training, which results in an anomaly detector that is significantly more robust to the presence of outliers during training.