Exploring Deep Anomaly Detection Methods Based on Capsule Net

07/15/2019
by   Xiaoyan Li, et al.
2

In this paper, we develop and explore deep anomaly detection techniques based on the capsule network (CapsNet) for image data. Being able to encoding intrinsic spatial relationship between parts and a whole, CapsNet has been applied as both a classifier and deep autoencoder. This inspires us to design a prediction-probability-based and a reconstruction-error-based normality score functions for evaluating the "outlierness" of unseen images. Our results on three datasets demonstrate that the prediction-probability-based method performs consistently well, while the reconstruction-error-based approach is relatively sensitive to the similarity between labeled and unlabeled images. Furthermore, both of the CapsNet-based methods outperform the principled benchmark methods in many cases.

READ FULL TEXT

page 3

page 4

research
02/22/2023

Robust and Explainable Contextual Anomaly Detection using Quantile Regression Forests

Traditional anomaly detection methods aim to identify objects that devia...
research
05/24/2023

Beyond Individual Input for Deep Anomaly Detection on Tabular Data

Anomaly detection is crucial in various domains, such as finance, health...
research
08/29/2020

Improved anomaly detection by training an autoencoder with skip connections on images corrupted with Stain-shaped noise

In industrial vision, the anomaly detection problem can be addressed wit...
research
06/17/2022

Multi-Contextual Predictions with Vision Transformer for Video Anomaly Detection

Video Anomaly Detection(VAD) has been traditionally tackled in two main ...
research
05/25/2016

Deep Structured Energy Based Models for Anomaly Detection

In this paper, we attack the anomaly detection problem by directly model...
research
01/27/2021

Autoencoder-based Condition Monitoring and Anomaly Detection Method for Rotating Machines

Rotating machines like engines, pumps, or turbines are ubiquitous in mod...
research
09/06/2020

Anomaly Detection With Partitioning Overfitting Autoencoder Ensembles

In this paper, we propose POTATOES (Partitioning OverfiTing AuTOencoder ...

Please sign up or login with your details

Forgot password? Click here to reset