# Discrete neural representations for explainable anomaly detection

arXiv: https://arxiv.org/abs/2112.05585 · HTML: https://mlsanity.com/paper/2112.05585/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 10 Dec 2021.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Likelihood Ratios for Out-of-Distribution Detection](https://mlsanity.com/paper/1906.02845/) (2019)
- [Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data](https://mlsanity.com/paper/2002.11297/) (2020)
- [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)
- [DRG: Dual Relation Graph for Human-Object Interaction Detection](https://mlsanity.com/paper/2008.11714/) (2020)
- [Towards Visually Explaining Variational Autoencoders](https://mlsanity.com/paper/1911.07389/) (2019)
- [Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video](https://mlsanity.com/paper/1812.04960/) (2018)
- [Abnormal Event Detection in Videos using Generative Adversarial Nets](https://mlsanity.com/paper/1708.09644/) (2017)
- [The AVA-Kinetics Localized Human Actions Video Dataset](https://mlsanity.com/paper/2005.00214/) (2020)
- [Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledge](https://mlsanity.com/paper/1709.09121/) (2017)
- [Detecting abnormal events in video using Narrowed Normality Clusters](https://mlsanity.com/paper/1801.05030/) (2018)
- [Training Adversarial Discriminators for Cross-channel Abnormal Event Detection in Crowds](https://mlsanity.com/paper/1706.07680/) (2017)
- [Real-Time Anomaly Detection and Localization in Crowded Scenes](https://mlsanity.com/paper/1511.06936/) (2015)
- [X-MAN: Explaining multiple sources of anomalies in video](https://mlsanity.com/paper/2106.08856/) (2021)

## Built on by (most cited first, 12 of 12)

- [A Survey on Explainable Anomaly Detection](https://mlsanity.com/paper/2210.06959/) (2022)
- [DyAnNet: A Scene Dynamicity Guided Self-Trained Video Anomaly Detection Network](https://mlsanity.com/paper/2211.00882/) (2022)
- [SynergyNet: Bridging the Gap between Discrete and Continuous Representations for Precise Medical Image Segmentation](https://mlsanity.com/paper/2310.17764/) (2023)
- [Unveiling the Unseen: A Comprehensive Survey on Explainable Anomaly Detection in Images and Videos](https://mlsanity.com/paper/2302.06670/) (2023)
- [Dynamic Distinction Learning: Adaptive Pseudo Anomalies for Video Anomaly Detection](https://mlsanity.com/paper/2404.04986/) (2024)
- [Transparent Anomaly Detection via Concept-based Explanations](https://mlsanity.com/paper/2310.10702/) (2023)
- [Spatio-temporal predictive tasks for abnormal event detection in videos](https://mlsanity.com/paper/2210.15741/) (2022)
- [Fast Region of Interest Proposals on Maritime UAVs](https://mlsanity.com/paper/2301.11650/) (2023)
- [Detecting Contextual Anomalies by Discovering Consistent Spatial Regions](https://mlsanity.com/paper/2501.08470/) (2025)
- [An Integrated Framework for Multi-Granular Explanation of Video Summarization](https://mlsanity.com/paper/2405.10082/) (2024)
- [Advancing Video Anomaly Detection: A Bi-Directional Hybrid Framework for Enhanced Single- and Multi-Task Approaches](https://mlsanity.com/paper/2504.14753/) (2025)
- [An Experimental Study on Generating Plausible Textual Explanations for Video Summarization](https://mlsanity.com/paper/2509.26225/) (2025)

## Abstract (arXiv)

The aim of this work is to detect and automatically generate high-level explanations of anomalous events in video. Understanding the cause of an anomalous event is crucial as the required response is dependant on its nature and severity. Recent works typically use object or action classifier to detect and provide labels for anomalous events. However, this constrains detection systems to a finite set of known classes and prevents generalisation to unknown objects or behaviours. Here we show how to robustly detect anomalies without the use of object or action classifiers yet still recover the high level reason behind the event. We make the following contributions: (1) a method using saliency maps to decouple the explanation of anomalous events from object and action classifiers, (2) show how to improve the quality of saliency maps using a novel neural architecture for learning discrete representations of video by predicting future frames and (3) beat the state-of-the-art anomaly explanation methods by 60% on a subset of the public benchmark X-MAN dataset.