Semi-supervised Anomaly Detection using Auto Encoders

A convolutional auto encoder based approach for semi-supervised anomaly detection in images.

In this article, I’ll be discussing a paper [1] that proposes an AutoEncoder based approach for the task of semi-supervised anomaly detection. If you want to look at the GitHub repository link, results and conclusion directly, please scroll to the bottom of the article.

Introduction

Anomaly detection refers to the task of finding unusual instances that stand out from the normal data [1]. The non-conforming patterns can be referred to using different names depending on the application area/domain, such as anomalies, outliers, exceptions, defects, containments, etc. [2] In several applications, these outliers or anomalous samples are of greater interest compared to the normal ones. Specifically in the case of industrial surface inspection and infrastructure asset management, finding defects (anomalous regions) is of extreme importance.

But there are several challenges that make this a difficult task.

Challenges in Anomaly Detection [2]

There are several challenges in anomaly detection and a few of the major ones are explained below.

1. Definition of the normal region which encompasses every possible normal behavior is extremely challenging.
2. Even noise is different…