# Robust Semi-Supervised Anomaly Detection via Adversarially Learned Continuous Noise Corruption

arXiv: https://arxiv.org/abs/2303.03925 · HTML: https://mlsanity.com/paper/2303.03925/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 2 Mar 2023.

## Builds on (most cited first, 19 of 19)

- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery](https://mlsanity.com/paper/1703.05921/) (2017)
- [GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training](https://mlsanity.com/paper/1805.06725/) (2018)
- [Adversarial Feature Learning](https://mlsanity.com/paper/1605.09782/) (2016)
- [Focal Frequency Loss for Image Reconstruction and Synthesis](https://mlsanity.com/paper/2012.12821/) (2020)
- [OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations](https://mlsanity.com/paper/1903.08550/) (2019)
- [Latent Space Autoregression for Novelty Detection](https://mlsanity.com/paper/1807.01653/) (2018)
- [An open access repository of images on plant health to enable the development of mobile disease diagnostics](https://mlsanity.com/paper/1511.08060/) (2015)
- [Efficient GAN-Based Anomaly Detection](https://mlsanity.com/paper/1802.06222/) (2018)
- [Generalized Denoising Auto-Encoders as Generative Models](https://mlsanity.com/paper/1305.6663/) (2013)
- [Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection](https://mlsanity.com/paper/1901.08954/) (2019)
- [Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection](https://mlsanity.com/paper/1806.04808/) (2018)
- [Deep Weakly-supervised Anomaly Detection](https://mlsanity.com/paper/1910.13601/) (2019)
- [ARAE: Adversarially Robust Training of Autoencoders Improves Novelty Detection](https://mlsanity.com/paper/2003.05669/) (2020)
- [Anomaly Detection with Adversarial Dual Autoencoders](https://mlsanity.com/paper/1902.06924/) (2019)
- [OLED: One-Class Learned Encoder-Decoder Network with Adversarial Context Masking for Novelty Detection](https://mlsanity.com/paper/2103.14953/) (2021)
- [Evaluation of a Dual Convolutional Neural Network Architecture for Object-wise Anomaly Detection in Cluttered X-ray Security Imagery](https://mlsanity.com/paper/1904.05304/) (2019)
- [On the Impact of Object and Sub-component Level Segmentation Strategies for Supervised Anomaly Detection within X-ray Security Imagery](https://mlsanity.com/paper/1911.08216/) (2019)
- [PANDA : Perceptually Aware Neural Detection of Anomalies](https://mlsanity.com/paper/2104.13702/) (2021)

## Built on by (most cited first, 2 of 2)

- [Diffusion-Scheduled Denoising Autoencoders for Anomaly Detection in Tabular Data](https://mlsanity.com/paper/2508.00758/) (2025)
- [A Robust Likelihood Model for Novelty Detection](https://mlsanity.com/paper/2306.03331/) (2023)

## Abstract (arXiv)

Anomaly detection is the task of recognising novel samples which deviate significantly from pre-establishednormality. Abnormal classes are not present during training meaning that models must learn effective rep-resentations solely across normal class data samples. Deep Autoencoders (AE) have been widely used foranomaly detection tasks, but suffer from overfitting to a null identity function. To address this problem, weimplement a training scheme applied to a Denoising Autoencoder (DAE) which introduces an efficient methodof producing Adversarially Learned Continuous Noise (ALCN) to maximally globally corrupt the input priorto denoising. Prior methods have applied similar approaches of adversarial training to increase the robustnessof DAE, however they exhibit limitations such as slow inference speed reducing their real-world applicabilityor producing generalised obfuscation which is more trivial to denoise. We show through rigorous evaluationthat our ALCN method of regularisation during training improves AUC performance during inference whileremaining efficient over both classical, leave-one-out novelty detection tasks with the variations-: 9 (normal)vs. 1 (abnormal) & 1 (normal) vs. 9 (abnormal); MNIST - AUCavg: 0.890 & 0.989, CIFAR-10 - AUCavg: 0.670& 0.742, in addition to challenging real-world anomaly detection tasks: industrial inspection (MVTEC-AD -AUCavg: 0.780) and plant disease detection (Plant Village - AUC: 0.770) when compared to prior approaches.