# Learning Competitive and Discriminative Reconstructions for Anomaly Detection

arXiv: https://arxiv.org/abs/1903.07058 · HTML: https://mlsanity.com/paper/1903.07058/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2019.

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

- [Generalized Out-of-Distribution Detection: A Survey](https://mlsanity.com/paper/2110.11334/) (2021)
- [Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection](https://mlsanity.com/paper/2203.12840/) (2022)
- [LARA: A Light and Anti-overfitting Retraining Approach for Unsupervised Time Series Anomaly Detection](https://mlsanity.com/paper/2310.05668/) (2023)
- [Enhancing Unsupervised Anomaly Detection with Score-Guided Network](https://mlsanity.com/paper/2109.04684/) (2021)
- [Cluster-Wide Task Slowdown Detection in Cloud System](https://mlsanity.com/paper/2408.04236/) (2024)
- [CSCAD: Correlation Structure-based Collective Anomaly Detection in Complex System](https://mlsanity.com/paper/2105.14476/) (2021)
- [Towards Black-box Adversarial Example Detection: A Data Reconstruction-based Method](https://mlsanity.com/paper/2306.02021/) (2023)
- [Synergizing Large Language Models and Task-specific Models for Time Series Anomaly Detection](https://mlsanity.com/paper/2501.05675/) (2025)
- [The Over-Certainty Phenomenon in Modern Test-Time Adaptation Algorithms](https://mlsanity.com/paper/2404.16168/) (2024)

## Abstract (arXiv)

Most of the existing methods for anomaly detection use only positive data to learn the data distribution, thus they usually need a pre-defined threshold at the detection stage to determine whether a test instance is an outlier. Unfortunately, a good threshold is vital for the performance and it is really hard to find an optimal one. In this paper, we take the discriminative information implied in unlabeled data into consideration and propose a new method for anomaly detection that can learn the labels of unlabelled data directly. Our proposed method has an end-to-end architecture with one encoder and two decoders that are trained to model inliers and outliers' data distributions in a competitive way. This architecture works in a discriminative manner without suffering from overfitting, and the training algorithm of our model is adopted from SGD, thus it is efficient and scalable even for large-scale datasets. Empirical studies on 7 datasets including KDD99, MNIST, Caltech-256, and ImageNet etc. show that our model outperforms the state-of-the-art methods.