Mirrored Autoencoders with Simplex Interpolation for Unsupervised Anomaly Detection

03/24/2020
by   Y. Wu, et al.
9

Use of deep generative models for unsupervised anomaly detection has shown great promise partially owing to their ability to learn proper representations of complex input data distributions. Current methods, however, lack a strong latent representation of the data, thereby resulting in sub-optimal unsupervised anomaly detection results. In this work, we propose a novel representation learning technique using deep autoencoders to tackle the problem of unsupervised anomaly detection. Our approach replaces the L_p reconstruction loss in the autoencoder optimization objective with a novel adversarial loss to enforce semantic-level reconstruction. In addition, we propose a novel simplex interpolation loss to improve the structure of the latent space representation in the autoencoder. Our technique improves the state-of-the-art unsupervised anomaly detection performance by a large margin on several image datasets including MNIST, fashion MNIST, CIFAR and Coil-100 as well as on several non-image datasets including KDD99, Arrhythmia and Thyroid. For example, On the CIFAR-10 dataset, using a standard leave-one-out evaluation protocol, our method achieves a substantial performance gain of 0.23 AUC points compared to the state-of-the-art.

READ FULL TEXT

page 4

page 22

research
04/26/2021

ODDObjects: A Framework for Multiclass Unsupervised Anomaly Detection on Masked Objects

This paper presents a novel framework for unsupervised anomaly detection...
research
03/08/2021

Anomaly Detection Based on Selection and Weighting in Latent Space

With the high requirements of automation in the era of Industry 4.0, ano...
research
10/05/2020

Deep Anomaly Detection by Residual Adaptation

Deep anomaly detection is a difficult task since, in high dimensions, it...
research
07/18/2020

DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection

One pivot challenge for image anomaly (AD) detection is to learn discrim...
research
02/25/2022

Do autoencoders need a bottleneck for anomaly detection?

A common belief in designing deep autoencoders (AEs), a type of unsuperv...
research
12/01/2020

Unsupervised Anomaly Detection From Semantic Similarity Scores

In this paper, we present SemSAD, a simple and generic framework for det...
research
04/22/2021

Unsupervised anomaly detection for a Smart Autonomous Robotic Assistant Surgeon (SARAS)using a deep residual autoencoder

Anomaly detection in Minimally-Invasive Surgery (MIS) traditionally requ...

Please sign up or login with your details

Forgot password? Click here to reset