# Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm

arXiv: https://arxiv.org/abs/2004.07657 · HTML: https://mlsanity.com/paper/2004.07657/

## Key facts

- Cited by 115 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2020.

## Built on by (most cited first, 30 of 115)

- [Anomaly Detection via Reverse Distillation from One-Class Embedding](https://mlsanity.com/paper/2201.10703/) (2022)
- [A Unified Model for Multi-class Anomaly Detection](https://mlsanity.com/paper/2206.03687/) (2022)
- [A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges](https://mlsanity.com/paper/2110.14051/) (2021)
- [Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection](https://mlsanity.com/paper/2111.09099/) (2021)
- [Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection](https://mlsanity.com/paper/2203.14506/) (2022)
- [Generative Cooperative Learning for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2203.03962/) (2022)
- [UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection](https://mlsanity.com/paper/2111.08644/) (2021)
- [Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts](https://mlsanity.com/paper/2403.06495/) (2024)
- [Harnessing Large Language Models for Training-free Video Anomaly Detection](https://mlsanity.com/paper/2404.01014/) (2024)
- [Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2203.00259/) (2022)
- [Explainable Deep Few-shot Anomaly Detection with Deviation Networks](https://mlsanity.com/paper/2108.00462/) (2021)
- [Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models](https://mlsanity.com/paper/2302.05087/) (2023)
- [Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection](https://mlsanity.com/paper/2306.14451/) (2023)
- [A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation](https://mlsanity.com/paper/2305.13611/) (2023)
- [Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors](https://mlsanity.com/paper/2306.12041/) (2023)
- [One-Class Classification: A Survey](https://mlsanity.com/paper/2101.03064/) (2021)
- [Anomaly Detection under Distribution Shift](https://mlsanity.com/paper/2303.13845/) (2023)
- [Learning Not to Reconstruct Anomalies](https://mlsanity.com/paper/2110.09742/) (2021)
- [ADTR: Anomaly Detection Transformer with Feature Reconstruction](https://mlsanity.com/paper/2209.01816/) (2022)
- [AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection](https://mlsanity.com/paper/2505.09926/) (2025)
- [Deep Learning for Video Anomaly Detection: A Review](https://mlsanity.com/paper/2409.05383/) (2024)
- [Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detection](https://mlsanity.com/paper/2110.09768/) (2021)
- [DyAnNet: A Scene Dynamicity Guided Self-Trained Video Anomaly Detection Network](https://mlsanity.com/paper/2211.00882/) (2022)
- [Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection](https://mlsanity.com/paper/2310.12790/) (2023)
- [Exploring Diffusion Models for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2304.05841/) (2023)
- [Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection](https://mlsanity.com/paper/2112.03649/) (2021)
- [Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2410.10289/) (2024)
- [Deep Anomaly Discovery From Unlabeled Videos via Normality Advantage and Self-Paced Refinement](https://mlsanity.com/paper/2108.01975/) (2021)
- [Networking Systems for Video Anomaly Detection: A Tutorial and Survey](https://mlsanity.com/paper/2405.10347/) (2024)
- [Cross-Domain Video Anomaly Detection without Target Domain Adaptation](https://mlsanity.com/paper/2212.07010/) (2022)

## Abstract (arXiv)

A popular method for anomaly detection is to use the generator of an adversarial network to formulate anomaly scores over reconstruction loss of input. Due to the rare occurrence of anomalies, optimizing such networks can be a cumbersome task. Another possible approach is to use both generator and discriminator for anomaly detection. However, attributed to the involvement of adversarial training, this model is often unstable in a way that the performance fluctuates drastically with each training step. In this study, we propose a framework that effectively generates stable results across a wide range of training steps and allows us to use both the generator and the discriminator of an adversarial model for efficient and robust anomaly detection. Our approach transforms the fundamental role of a discriminator from identifying real and fake data to distinguishing between good and bad quality reconstructions. To this end, we prepare training examples for the good quality reconstruction by employing the current generator, whereas poor quality examples are obtained by utilizing an old state of the same generator. This way, the discriminator learns to detect subtle distortions that often appear in reconstructions of the anomaly inputs. Extensive experiments performed on Caltech-256 and MNIST image datasets for novelty detection show superior results. Furthermore, on UCSD Ped2 video dataset for anomaly detection, our model achieves a frame-level AUC of 98.1%, surpassing recent state-of-the-art methods.