Anomaly Detection with Adversarially Learned Perturbations of Latent Space

TL;DR

This paper introduces an adversarial framework for anomaly detection that enhances latent space representations by training a perturbation generator and autoencoder adversarially, leading to improved detection performance.

Contribution

The work proposes a novel adversarial training method involving a perturbation generator and autoencoder to produce richer representations for anomaly detection.

Findings

Outperforms state-of-the-art methods on image datasets

Effective in both image and video anomaly detection

Learns semantically richer latent representations

Abstract

Anomaly detection is to identify samples that do not conform to the distribution of the normal data. Due to the unavailability of anomalous data, training a supervised deep neural network is a cumbersome task. As such, unsupervised methods are preferred as a common approach to solve this task. Deep autoencoders have been broadly adopted as a base of many unsupervised anomaly detection methods. However, a notable shortcoming of deep autoencoders is that they provide insufficient representations for anomaly detection by generalizing to reconstruct outliers. In this work, we have designed an adversarial framework consisting of two competing components, an Adversarial Distorter, and an Autoencoder. The Adversarial Distorter is a convolutional encoder that learns to produce effective perturbations and the autoencoder is a deep convolutional neural network that aims to reconstruct the images from the perturbed latent feature space. The networks are trained with opposing goals in which the Adversarial Distorter produces perturbations that are applied to the encoder's latent feature space to maximize the reconstruction error and the autoencoder tries to neutralize the effect of these perturbations to minimize it. When applied to anomaly detection, the proposed method learns semantically richer representations due to applying perturbations to the feature space. The proposed method outperforms the existing state-of-the-art methods in anomaly detection on image and video datasets.