Advancing unsupervised anomaly detection with normalizing flow and multi-scale ensemble learning

Visual anomaly detection plays a crucial role in manufacturing to ensure product quality by identifying image patterns that deviate from the expected ones. Existing methods that rely on distribution estimation struggle with the complexity of real-world images, resulting in complex and inefficient pr...

Descripción completa

Detalles Bibliográficos
Autores: Campos-Romero, Miguel, Carranza García, Manuel, Riquelme Santos, José Cristóbal
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2024
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/165589
Acceso en línea:https://hdl.handle.net/11441/165589
https://doi.org/10.1016/j.engappai.2024.109088
Access Level:acceso abierto
Palabra clave:Anomaly detection
Novelty detection
Deep learning
Normalizing flow
Unsupervised learning
id ES_d73d30bbd6398f8dc6e00853de71f5ed
oai_identifier_str oai:idus.us.es:11441/165589
network_acronym_str ES
network_name_str España
repository_id_str
spelling Advancing unsupervised anomaly detection with normalizing flow and multi-scale ensemble learningCampos-Romero, MiguelCarranza García, ManuelRiquelme Santos, José CristóbalAnomaly detectionNovelty detectionDeep learningNormalizing flowUnsupervised learningVisual anomaly detection plays a crucial role in manufacturing to ensure product quality by identifying image patterns that deviate from the expected ones. Existing methods that rely on distribution estimation struggle with the complexity of real-world images, resulting in complex and inefficient procedures. This study leverages normalizing flow techniques to address the cold start anomaly detection problem, where no prior examples of anomalies are available during the training phase. In such scenarios, models must learn exclusively from defect-free images and still accurately identify anomalies. We propose a novel unsupervised multi-scale and multi-semantic normalizing flow model, enhanced with an ensemble of neural networks, to detect anomalies based on their feature distributions. Our model estimates the likelihood of non-defective features, identifying anomalies as out-of-distribution values. Extensive experiments on three state-of-the-art anomaly detection datasets demonstrate that our proposal achieves superior AUROC performance and improves computational efficiency compared to existing approaches. Furthermore, we validate the robustness and adaptability of our proposal through low-shot training experiments using only 20% of available training data, highlighting its potential as an efficient solution for cold start anomaly detection.Pergamon ElsevierLenguajes y Sistemas Informáticos2024info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/165589https://doi.org/10.1016/j.engappai.2024.109088reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésEngineering Applications of Artificial Intelligence, 137, 109088.https://www.sciencedirect.com/science/article/pii/S0952197624012466?via%3Dihubinfo:eu-repo/semantics/openAccessoai:idus.us.es:11441/1655892026-06-17T12:51:07Z
dc.title.none.fl_str_mv Advancing unsupervised anomaly detection with normalizing flow and multi-scale ensemble learning
title Advancing unsupervised anomaly detection with normalizing flow and multi-scale ensemble learning
spellingShingle Advancing unsupervised anomaly detection with normalizing flow and multi-scale ensemble learning
Campos-Romero, Miguel
Anomaly detection
Novelty detection
Deep learning
Normalizing flow
Unsupervised learning
title_short Advancing unsupervised anomaly detection with normalizing flow and multi-scale ensemble learning
title_full Advancing unsupervised anomaly detection with normalizing flow and multi-scale ensemble learning
title_fullStr Advancing unsupervised anomaly detection with normalizing flow and multi-scale ensemble learning
title_full_unstemmed Advancing unsupervised anomaly detection with normalizing flow and multi-scale ensemble learning
title_sort Advancing unsupervised anomaly detection with normalizing flow and multi-scale ensemble learning
dc.creator.none.fl_str_mv Campos-Romero, Miguel
Carranza García, Manuel
Riquelme Santos, José Cristóbal
author Campos-Romero, Miguel
author_facet Campos-Romero, Miguel
Carranza García, Manuel
Riquelme Santos, José Cristóbal
author_role author
author2 Carranza García, Manuel
Riquelme Santos, José Cristóbal
author2_role author
author
dc.contributor.none.fl_str_mv Lenguajes y Sistemas Informáticos
dc.subject.none.fl_str_mv Anomaly detection
Novelty detection
Deep learning
Normalizing flow
Unsupervised learning
topic Anomaly detection
Novelty detection
Deep learning
Normalizing flow
Unsupervised learning
description Visual anomaly detection plays a crucial role in manufacturing to ensure product quality by identifying image patterns that deviate from the expected ones. Existing methods that rely on distribution estimation struggle with the complexity of real-world images, resulting in complex and inefficient procedures. This study leverages normalizing flow techniques to address the cold start anomaly detection problem, where no prior examples of anomalies are available during the training phase. In such scenarios, models must learn exclusively from defect-free images and still accurately identify anomalies. We propose a novel unsupervised multi-scale and multi-semantic normalizing flow model, enhanced with an ensemble of neural networks, to detect anomalies based on their feature distributions. Our model estimates the likelihood of non-defective features, identifying anomalies as out-of-distribution values. Extensive experiments on three state-of-the-art anomaly detection datasets demonstrate that our proposal achieves superior AUROC performance and improves computational efficiency compared to existing approaches. Furthermore, we validate the robustness and adaptability of our proposal through low-shot training experiments using only 20% of available training data, highlighting its potential as an efficient solution for cold start anomaly detection.
publishDate 2024
dc.date.none.fl_str_mv 2024
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/165589
https://doi.org/10.1016/j.engappai.2024.109088
url https://hdl.handle.net/11441/165589
https://doi.org/10.1016/j.engappai.2024.109088
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Engineering Applications of Artificial Intelligence, 137, 109088.
https://www.sciencedirect.com/science/article/pii/S0952197624012466?via%3Dihub
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Pergamon Elsevier
publisher.none.fl_str_mv Pergamon Elsevier
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869420984102027264
score 15,811543

Similares en LA Referencia