Research

Paper

TESTING March 25, 2026

MLE-UVAD: Minimal Latent Entropy Autoencoder for Fully Unsupervised Video Anomaly Detection

Authors

Yuang Geng, Junkai Zhou, Kang Yang, Pan He, Zhuoyang Zhou, Jose C. Principe, Joel Harley, Ivan Ruchkin

Abstract

In this paper, we address the challenging problem of single-scene, fully unsupervised video anomaly detection (VAD), where raw videos containing both normal and abnormal events are used directly for training and testing without any labels. This differs sharply from prior work that either requires extensive labeling (fully or weakly supervised) or depends on normal-only videos (one-class classification), which are vulnerable to distribution shifts and contamination. We propose an entropy-guided autoencoder that detects anomalies through reconstruction error by reconstructing normal frames well while making anomalies reconstruct poorly. The key idea is to combine the standard reconstruction loss with a novel Minimal Latent Entropy (MLE) loss in the autoencoder. Reconstruction loss alone maps normal and abnormal inputs to distinct latent clusters due to their inherent differences, but also risks reconstructing anomalies too well to detect. Therefore, MLE loss addresses this by minimizing the entropy of latent embeddings, encouraging them to concentrate around high-density regions. Since normal frames dominate the raw video, sparse anomalous embeddings are pulled into the normal cluster, so the decoder emphasizes normal patterns and produces poor reconstructions for anomalies. This dual-loss design produces a clear reconstruction gap that enables effective anomaly detection. Extensive experiments on two widely used benchmarks and a challenging self-collected driving dataset demonstrate that our method achieves robust and superior performance over baselines.

Metadata

arXiv ID: 2603.23868
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-25
Fetched: 2026-03-26 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.23868v1</id>\n    <title>MLE-UVAD: Minimal Latent Entropy Autoencoder for Fully Unsupervised Video Anomaly Detection</title>\n    <updated>2026-03-25T02:51:26Z</updated>\n    <link href='https://arxiv.org/abs/2603.23868v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.23868v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>In this paper, we address the challenging problem of single-scene, fully unsupervised video anomaly detection (VAD), where raw videos containing both normal and abnormal events are used directly for training and testing without any labels. This differs sharply from prior work that either requires extensive labeling (fully or weakly supervised) or depends on normal-only videos (one-class classification), which are vulnerable to distribution shifts and contamination. We propose an entropy-guided autoencoder that detects anomalies through reconstruction error by reconstructing normal frames well while making anomalies reconstruct poorly. The key idea is to combine the standard reconstruction loss with a novel Minimal Latent Entropy (MLE) loss in the autoencoder. Reconstruction loss alone maps normal and abnormal inputs to distinct latent clusters due to their inherent differences, but also risks reconstructing anomalies too well to detect. Therefore, MLE loss addresses this by minimizing the entropy of latent embeddings, encouraging them to concentrate around high-density regions. Since normal frames dominate the raw video, sparse anomalous embeddings are pulled into the normal cluster, so the decoder emphasizes normal patterns and produces poor reconstructions for anomalies. This dual-loss design produces a clear reconstruction gap that enables effective anomaly detection. Extensive experiments on two widely used benchmarks and a challenging self-collected driving dataset demonstrate that our method achieves robust and superior performance over baselines.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-25T02:51:26Z</published>\n    <arxiv:comment>Submitted to ECCV 2026. 18 pages, 8 figures. Includes supplementary material</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Yuang Geng</name>\n    </author>\n    <author>\n      <name>Junkai Zhou</name>\n    </author>\n    <author>\n      <name>Kang Yang</name>\n    </author>\n    <author>\n      <name>Pan He</name>\n    </author>\n    <author>\n      <name>Zhuoyang Zhou</name>\n    </author>\n    <author>\n      <name>Jose C. Principe</name>\n    </author>\n    <author>\n      <name>Joel Harley</name>\n    </author>\n    <author>\n      <name>Ivan Ruchkin</name>\n    </author>\n  </entry>"
}