# Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomalies

arXiv: https://arxiv.org/abs/2203.13716 · HTML: https://mlsanity.com/paper/2203.13716/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 93 references that are in the map.
- First posted on arXiv 25 Mar 2022.

## Builds on (most cited first, 30 of 36)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [Learning Memory-guided Normality for Anomaly Detection](https://mlsanity.com/paper/2003.13228/) (2020)
- [Learning Temporal Regularity in Video Sequences](https://mlsanity.com/paper/1604.04574/) (2016)
- [Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection](https://mlsanity.com/paper/1903.07256/) (2019)
- [Latent Space Autoregression for Novelty Detection](https://mlsanity.com/paper/1807.01653/) (2018)
- [Anomaly Detection in Video Sequence with Appearance-Motion Correspondence](https://mlsanity.com/paper/1908.06351/) (2019)
- [Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm](https://mlsanity.com/paper/2004.07657/) (2020)
- [Deep Structured Energy Based Models for Anomaly Detection](https://mlsanity.com/paper/1605.07717/) (2016)
- [Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video](https://mlsanity.com/paper/1812.04960/) (2018)
- [Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening](https://mlsanity.com/paper/1903.08297/) (2019)
- [Abnormal Event Detection in Videos using Generative Adversarial Nets](https://mlsanity.com/paper/1708.09644/) (2017)
- [Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection](https://mlsanity.com/paper/1806.04808/) (2018)
- [CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection](https://mlsanity.com/paper/2011.12077/) (2020)
- [Learning Deep Representations of Appearance and Motion for Anomalous Event Detection](https://mlsanity.com/paper/1510.01553/) (2015)
- [Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledge](https://mlsanity.com/paper/1709.09121/) (2017)
- [Unmasking the abnormal events in video](https://mlsanity.com/paper/1705.08182/) (2017)
- [Detecting and classifying lesions in mammograms with Deep Learning](https://mlsanity.com/paper/1707.08401/) (2017)
- [Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detection](https://mlsanity.com/paper/1610.00307/) (2016)
- [Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification](https://mlsanity.com/paper/1612.05968/) (2016)
- [Training Adversarial Discriminators for Cross-channel Abnormal Event Detection in Crowds](https://mlsanity.com/paper/1706.07680/) (2017)
- [A Self-Reasoning Framework for Anomaly Detection Using Video-Level Labels](https://mlsanity.com/paper/2008.11887/) (2020)
- [Dual Principal Component Pursuit](https://mlsanity.com/paper/1510.04390/) (2015)
- [Provable Self-Representation Based Outlier Detection in a Union of Subspaces](https://mlsanity.com/paper/1704.03925/) (2017)
- [STAN: Spatio-Temporal Adversarial Networks for Abnormal Event Detection](https://mlsanity.com/paper/1804.08381/) (2018)

## Built on by (most cited first, 14 of 14)

- [Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2404.08531/) (2024)
- [Deep Learning for Video Anomaly Detection: A Review](https://mlsanity.com/paper/2409.05383/) (2024)
- [Exploring Diffusion Models for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2304.05841/) (2023)
- [Detecting Generated Images by Real Images Only](https://mlsanity.com/paper/2311.00962/) (2023)
- [A Coarse-to-Fine Pseudo-Labeling (C2FPL) Framework for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2310.17650/) (2023)
- [Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach](https://mlsanity.com/paper/2311.16514/) (2023)
- [AVadCLIP: Audio-Visual Collaboration for Robust Video Anomaly Detection](https://mlsanity.com/paper/2504.04495/) (2025)
- [Vision-Language Models Assisted Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2409.14109/) (2024)
- [Exploiting Autoencoder's Weakness to Generate Pseudo Anomalies](https://mlsanity.com/paper/2405.05886/) (2024)
- [The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM](https://mlsanity.com/paper/2507.21649/) (2025)
- [Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection](https://mlsanity.com/paper/2405.02068/) (2024)
- [Open-set Anomaly Segmentation in Complex Scenarios](https://mlsanity.com/paper/2504.19706/) (2025)
- [RobustA: Robust Anomaly Detection in Multimodal Data](https://mlsanity.com/paper/2511.07276/) (2025)
- [Deep Convolutional Large-Margin ℓp-SVDD for Visual Anomaly Detection](https://mlsanity.com/paper/2607.22212/) (2026)

## Abstract (arXiv)

Recently, anomaly scores have been formulated using reconstruction loss of the adversarially learned generators and/or classification loss of discriminators. Unavailability of anomaly examples in the training data makes optimization of such networks challenging. Attributed to the adversarial training, performance of such models fluctuates drastically with each training step, making it difficult to halt the training at an optimal point. In the current study, we propose a robust anomaly detection framework that overcomes such instability by transforming the fundamental role of the discriminator from identifying real vs. fake data to distinguishing good vs. bad quality reconstructions. For this purpose, we propose a method that utilizes the current state as well as an old state of the same generator to create good and bad quality reconstruction examples. The discriminator is trained on these examples to detect the subtle distortions that are often present in the reconstructions of anomalous data. In addition, we propose an efficient generic criterion to stop the training of our model, ensuring elevated performance. Extensive experiments performed on six datasets across multiple domains including image and video based anomaly detection, medical diagnosis, and network security, have demonstrated excellent performance of our approach.