# Unsupervised Synthesis of Anomalies in Videos: Transforming the Normal

## TL;DR

This paper introduces an unsupervised method to generate abnormal video data from normal data using a multi-stage pipeline, enhancing anomaly detection by augmenting training datasets with synthesized anomalies.

## Contribution

It presents a novel unsupervised synthesis approach for abnormal video data, improving anomaly detection performance without requiring labeled abnormal samples.

## Key findings

- Achieves improved detection accuracy over previous probabilistic methods.
- Successfully generalizes across multiple real-world datasets.
- Demonstrates effective data augmentation for anomaly classification.

## Abstract

Abnormal activity recognition requires detection of occurrence of anomalous events that suffer from a severe imbalance in data. In a video, normal is used to describe activities that conform to usual events while the irregular events which do not conform to the normal are referred to as abnormal. It is far more common to observe normal data than to obtain abnormal data in visual surveillance. In this paper, we propose an approach where we can obtain abnormal data by transforming normal data. This is a challenging task that is solved through a multi-stage pipeline approach. We utilize a number of techniques from unsupervised segmentation in order to synthesize new samples of data that are transformed from an existing set of normal examples. Further, this synthesis approach has useful applications as a data augmentation technique. An incrementally trained Bayesian convolutional neural network (CNN) is used to carefully select the set of abnormal samples that can be added. Finally through this synthesis approach we obtain a comparable set of abnormal samples that can be used for training the CNN for the classification of normal vs abnormal samples. We show that this method generalizes to multiple settings by evaluating it on two real world datasets and achieves improved performance over other probabilistic techniques that have been used in the past for this task.