# Latent space conditioning for improved classification and anomaly detection

arXiv: https://arxiv.org/abs/1911.10599 · HTML: https://mlsanity.com/paper/1911.10599/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2019.

## Built on by (most cited first, 8 of 8)

- [Exploring the Potential of World Models for Anomaly Detection in Autonomous Driving](https://mlsanity.com/paper/2308.05701/) (2023)
- [k-NNN: Nearest Neighbors of Neighbors for Anomaly Detection](https://mlsanity.com/paper/2305.17695/) (2023)
- [VAE-iForest: Auto-encoding Reconstruction and Isolation-based Anomalies Detecting Fallen Objects on Road Surface](https://mlsanity.com/paper/2203.01193/) (2022)
- [Conditioning Latent-Space Clusters for Real-World Anomaly Classification](https://mlsanity.com/paper/2309.09676/) (2023)
- [Improved Anomaly Detection through Conditional Latent Space VAE Ensembles](https://mlsanity.com/paper/2410.12328/) (2024)
- [Evaluating the Stability of Deep Learning Latent Feature Spaces](https://mlsanity.com/paper/2402.11404/) (2024)
- [Learning Traffic Anomalies from Generative Models on Real-Time Observations](https://mlsanity.com/paper/2502.01391/) (2025)
- [Toward precision soil health: A regional framework for site-specific management across Missouri](https://mlsanity.com/paper/2510.26815/) (2025)

## Abstract (arXiv)

We propose a new type of variational autoencoder to perform improved pre-processing for clustering and anomaly detection on data with a given label. Anomalies however are not known or labeled. We call our method conditional latent space variational autonencoder since it separates the latent space by conditioning on information within the data. The method fits one prior distribution to each class in the dataset, effectively expanding the prior distribution to include a Gaussian mixture model. Our approach is compared against the capabilities of a typical variational autoencoder by measuring their V-score during cluster formation with respect to the k-means and EM algorithms. For anomaly detection, we use a new metric composed of the mass-volume and excess-mass curves which can work in an unsupervised setting. We compare the results between established methods such as as isolation forest, local outlier factor and one-class support vector machine.