# Constricting Normal Latent Space for Anomaly Detection with Normal-only Training Data

arXiv: https://arxiv.org/abs/2403.16270 · HTML: https://mlsanity.com/paper/2403.16270/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 24 Mar 2024.

## Builds on (most cited first, 13 of 13)

- [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)
- [Anomaly Detection in Video via Self-Supervised and Multi-Task Learning](https://mlsanity.com/paper/2011.07491/) (2020)
- [Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm](https://mlsanity.com/paper/2004.07657/) (2020)
- [G2D: Generate to Detect Anomaly](https://mlsanity.com/paper/2006.11629/) (2020)
- [Learning Not to Reconstruct Anomalies](https://mlsanity.com/paper/2110.09742/) (2021)
- [Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detection](https://mlsanity.com/paper/2110.09768/) (2021)
- [Limiting the Reconstruction Capability of Generative Neural Network using Negative Learning](https://mlsanity.com/paper/1708.08985/) (2017)
- [Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos](https://mlsanity.com/paper/2203.13704/) (2022)
- [Anomaly Detection in Particulate Matter Sensor using Hypothesis Pruning Generative Adversarial Network](https://mlsanity.com/paper/1912.00583/) (2019)

## Built on by (most cited first, 1 of 1)

- [Unsupervised Anomaly Detection in NSL-KDD Using β-VAE: A Latent Space and Reconstruction Error Approach](https://mlsanity.com/paper/2602.19785/) (2026)

## Abstract (arXiv)

In order to devise an anomaly detection model using only normal training data, an autoencoder (AE) is typically trained to reconstruct the data. As a result, the AE can extract normal representations in its latent space. During test time, since AE is not trained using real anomalies, it is expected to poorly reconstruct the anomalous data. However, several researchers have observed that it is not the case. In this work, we propose to limit the reconstruction capability of AE by introducing a novel latent constriction loss, which is added to the existing reconstruction loss. By using our method, no extra computational cost is added to the AE during test time. Evaluations using three video anomaly detection benchmark datasets, i.e., Ped2, Avenue, and ShanghaiTech, demonstrate the effectiveness of our method in limiting the reconstruction capability of AE, which leads to a better anomaly detection model.