CVAD - An unsupervised image anomaly detector[Formula presented]

Xiaoyuan Guo; Judy Wawira Gichoya; Saptarshi Purkayastha; Imon Banerjee

doi:10.1016/j.simpa.2021.100195

CVAD - An unsupervised image anomaly detector[Formula presented]

Xiaoyuan Guo, Judy Wawira Gichoya, Saptarshi Purkayastha, Imon Banerjee

Diagnostic Radiology

Research output: Contribution to journal › Article › peer-review

Abstract

Detecting out-of-distribution samples for image applications plays an important role in safeguarding the reliability of machine learning model deployment. In this article, we developed a software tool to support our OOD detector CVAD - a self-supervised Cascade Variational autoencoder-based Anomaly Detector, which can be easily applied to various image applications without any assumptions. The corresponding open-source software is published for better public research and tool usage.

Original language	English (US)
Article number	100195
Journal	Software Impacts
Volume	11
DOIs	https://doi.org/10.1016/j.simpa.2021.100195
State	Published - Feb 2022

Keywords

Anomaly detection
OOD detection
Variational autoencoder

ASJC Scopus subject areas

Software

Access to Document

10.1016/j.simpa.2021.100195

Cite this

@article{8a1ef63d04f84189b87c4607f54a9eec,

title = "CVAD - An unsupervised image anomaly detector[Formula presented]",

abstract = "Detecting out-of-distribution samples for image applications plays an important role in safeguarding the reliability of machine learning model deployment. In this article, we developed a software tool to support our OOD detector CVAD - a self-supervised Cascade Variational autoencoder-based Anomaly Detector, which can be easily applied to various image applications without any assumptions. The corresponding open-source software is published for better public research and tool usage.",

keywords = "Anomaly detection, OOD detection, Variational autoencoder",

author = "Xiaoyuan Guo and Gichoya, {Judy Wawira} and Saptarshi Purkayastha and Imon Banerjee",

note = "Publisher Copyright: {\textcopyright} 2021 The Author(s)",

year = "2022",

month = feb,

doi = "10.1016/j.simpa.2021.100195",

language = "English (US)",

volume = "11",

journal = "Software Impacts",

issn = "2665-9638",

publisher = "Elsevier BV",

}

TY - JOUR

T1 - CVAD - An unsupervised image anomaly detector[Formula presented]

AU - Guo, Xiaoyuan

AU - Gichoya, Judy Wawira

AU - Purkayastha, Saptarshi

AU - Banerjee, Imon

PY - 2022/2

Y1 - 2022/2

N2 - Detecting out-of-distribution samples for image applications plays an important role in safeguarding the reliability of machine learning model deployment. In this article, we developed a software tool to support our OOD detector CVAD - a self-supervised Cascade Variational autoencoder-based Anomaly Detector, which can be easily applied to various image applications without any assumptions. The corresponding open-source software is published for better public research and tool usage.

AB - Detecting out-of-distribution samples for image applications plays an important role in safeguarding the reliability of machine learning model deployment. In this article, we developed a software tool to support our OOD detector CVAD - a self-supervised Cascade Variational autoencoder-based Anomaly Detector, which can be easily applied to various image applications without any assumptions. The corresponding open-source software is published for better public research and tool usage.

KW - Anomaly detection

KW - OOD detection

KW - Variational autoencoder

UR - http://www.scopus.com/inward/record.url?scp=85121922829&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85121922829&partnerID=8YFLogxK

U2 - 10.1016/j.simpa.2021.100195

DO - 10.1016/j.simpa.2021.100195

M3 - Article

AN - SCOPUS:85121922829

SN - 2665-9638

VL - 11

JO - Software Impacts

JF - Software Impacts

M1 - 100195

ER -

CVAD - An unsupervised image anomaly detector[Formula presented]

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this