Leveraging Vector-Quantized Variational Autoencoder Inner Metrics for Anomaly Detection

Anomaly Detection (AD) is an important research topic, with very diverse applications such as industrial defect detection, medical diagnosis, fraud detection, intrusion detection, etc. Within the last few years, deep learning-based methods have become the standard approach for AD. In many practical...

Full description

Saved in:
Bibliographic Details
Published in:International Conference on Pattern Recognition pp. 435 - 441
Main Authors: Gangloff, Hugo, Pham, Minh-Tan, Courtrai, Luc, Lefevre, Sebastien
Format: Conference Proceeding
Language:English
Published: IEEE 21.08.2022
Subjects:
Intrusion detection
Learning systems
Machine learning
Measurement
Medical diagnosis
Pattern recognition
Training
ISSN:2831-7475
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Anomaly Detection (AD) is an important research topic, with very diverse applications such as industrial defect detection, medical diagnosis, fraud detection, intrusion detection, etc. Within the last few years, deep learning-based methods have become the standard approach for AD. In many practical cases, the anomalies are unknown in advance. Therefore, most of challenging AD problems need to be addressed in an unsupervised or weakly supervised framework. In this context, deep generative models are widely used, in particular Variational Autoencoder (VAE) models. VAEs have been extended to Vector-Quantized VAEs (VQ-VAEs), a model increasingly popular because of its versatility enabled by the discrete latent space. We present for the first time a robust approach which takes advantage of the inner metrics of VQ-VAEs for AD. We show that the distance between the output of the encoder and the codebook vectors of a VQ-VAE provides a valuable information which can be used to localize the anomalies. In our approach, this metric complements a reconstruction-based metric to improve AD results. We compare our model with state-of-the-art AD models on three standards datasets, including the MVTec, UCSD-Ped1 and CIFAR-10 datasets. Experiments show that the proposed method yields high competitive results.
AbstractList Anomaly Detection (AD) is an important research topic, with very diverse applications such as industrial defect detection, medical diagnosis, fraud detection, intrusion detection, etc. Within the last few years, deep learning-based methods have become the standard approach for AD. In many practical cases, the anomalies are unknown in advance. Therefore, most of challenging AD problems need to be addressed in an unsupervised or weakly supervised framework. In this context, deep generative models are widely used, in particular Variational Autoencoder (VAE) models. VAEs have been extended to Vector-Quantized VAEs (VQ-VAEs), a model increasingly popular because of its versatility enabled by the discrete latent space. We present for the first time a robust approach which takes advantage of the inner metrics of VQ-VAEs for AD. We show that the distance between the output of the encoder and the codebook vectors of a VQ-VAE provides a valuable information which can be used to localize the anomalies. In our approach, this metric complements a reconstruction-based metric to improve AD results. We compare our model with state-of-the-art AD models on three standards datasets, including the MVTec, UCSD-Ped1 and CIFAR-10 datasets. Experiments show that the proposed method yields high competitive results.
Author Gangloff, Hugo
Pham, Minh-Tan
Courtrai, Luc
Lefevre, Sebastien
Author_xml – sequence: 1
  givenname: Hugo
  surname: Gangloff
  fullname: Gangloff, Hugo
  email: hugo.gangloff@irisa.fr
  organization: Université Bretagne Sud,IRISA,Vannes,France,56000
– sequence: 2
  givenname: Minh-Tan
  surname: Pham
  fullname: Pham, Minh-Tan
  email: minh-tan.pham@irisa.fr
  organization: Université Bretagne Sud,IRISA,Vannes,France,56000
– sequence: 3
  givenname: Luc
  surname: Courtrai
  fullname: Courtrai, Luc
  email: luc.courtrai@irisa.fr
  organization: Université Bretagne Sud,IRISA,Vannes,France,56000
– sequence: 4
  givenname: Sebastien
  surname: Lefevre
  fullname: Lefevre, Sebastien
  email: sebastien.lefevre@irisa.fr
  organization: Université Bretagne Sud,IRISA,Vannes,France,56000
BookMark eNotkMtKAzEYRqMo2FafQJC8wNTcJpksh_FWqHhB67Jkkj810iaSSYX69Bbs5jurcxbfGJ3EFAGhK0qmlBJ9PeueX2vJJZ0ywthU61pSwo7QmEpZC00kE8doxBpOKyVUfYbGw_BFCCO8bkboYw4_kM0qxBVegC0pVy9bE0v4BYcXJgdTQopmjdttSRBtcpDxLMb9PkLJwQ7Yp4zbmDZmvcM3UPaRvXGOTr1ZD3Bx4AS9392-dQ_V_Ol-1rXz6pNxVSrvSWN7XStvRW-ds7KXXrhGCcKNNrZX3mneK-sMsdZRp5peN2C9oMYoQfkEXf53AwAsv3PYmLxbHk7gf13vVm8
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICPR56361.2022.9956102
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISBN 1665490624
9781665490627
EISSN 2831-7475
EndPage 441
ExternalDocumentID 9956102
Genre orig-research
GrantInformation_xml – fundername: European Maritime and Fisheries Fund
  funderid: 10.13039/100014510
GroupedDBID 6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-h237t-ff08cb957fc4bcddc6b6f4d87403a9acb7fd93b7cda0ccd1d78b98ecf41aa7413
IEDL.DBID RIE
ISICitedReferencesCount 7
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000897707600060&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:18:27 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-h237t-ff08cb957fc4bcddc6b6f4d87403a9acb7fd93b7cda0ccd1d78b98ecf41aa7413
PageCount 7
ParticipantIDs ieee_primary_9956102
PublicationCentury 2000
PublicationDate 2022-Aug.-21
PublicationDateYYYYMMDD 2022-08-21
PublicationDate_xml – month: 08
  year: 2022
  text: 2022-Aug.-21
  day: 21
PublicationDecade 2020
PublicationTitle International Conference on Pattern Recognition
PublicationTitleAbbrev ICPR
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0020358
Score 2.3029745
Snippet Anomaly Detection (AD) is an important research topic, with very diverse applications such as industrial defect detection, medical diagnosis, fraud detection,...
SourceID ieee
SourceType Publisher
StartPage 435
SubjectTerms Intrusion detection
Learning systems
Machine learning
Measurement
Medical diagnosis
Pattern recognition
Training
Title Leveraging Vector-Quantized Variational Autoencoder Inner Metrics for Anomaly Detection
URI https://ieeexplore.ieee.org/document/9956102
WOSCitedRecordID wos000897707600060&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA61eNBLta34JgePbptNdrObY6kWhVqqaO2t5IkF3ZV2V9Bfb5KuVcGLtySQBGbymJnkmw-AM65wJHhMAokUDSKsRZBiLgKDCCZM2rong5kMk9EonU7ZuAbO11gYrbX_fKY7rujf8lUuSxcq63oUpsscuZEkdIXVWjtXiMRphQAOEete98d3MSXUuYAYd6qevyhU_A0yaPxv7h3Q_obiwfH6ktkFNZ01QeOLiwFWW7MJtn8kFmyBx6G2S9QTEMGJj8sHt6WV4fxDKzix7nEVAoS9sshdKktlx7p2LFzwxlFsySW0xizsZfkLf36HF7rwP7ayNngYXN73r4KKQiF4wiQpAmNQKgWLEyMjIZWSVFATKcfDRzjjUiRGMSISqTiSUoUqSQVLtTRRyLk1NsgeqGd5pvcBpDTlzNoXQlsbC1HOIiW5MtQeCYgKgg5Ay0lt9rrKkjGrBHb4d_MR2HKKcdFZHB6DerEo9QnYlG_FfLk49ar9BHb7p-w
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG6ImqgXFDC-7cGjC912t7s9EpRAXAgaRG6kr40kuhhYTPTX25YVNfHirW3SNpnpY2babz4ALrnCgeAh8SRS1AuwFl6MufBSRDBh0tQdGcwoifr9eDxmgxK4WmNhtNbu85mu26J7y1czubShsoZDYdrMkZthEGC0Qmut3StEwrjAAPuINbqtwX1ICbVOIMb1ou8vEhV3h7TL_5t9D9S-wXhwsL5m9kFJZxVQ_mJjgMXmrIDdH6kFq-Ax0WaROgoiOHKRee9uaaQ4_dAKjoyDXAQBYXOZz2wyS2XG6loeLtizJFtyAY05C5vZ7IU_v8Nrnbs_W1kNPLRvhq2OV5AoeE-YRLmXpiiWgoVRKgMhlZJU0DRQlomPcMaliFLFiIik4khK5asoFizWMg18zo25QQ7ARjbL9CGAlMacGQtDaGNlIcpZoCRXKTWHAqKCoCNQtVKbvK7yZEwKgR3_3XwBtjvDXjJJuv3bE7BjlWRjtdg_BRv5fKnPwJZ8y6eL-blT8yddt6sz
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=International+Conference+on+Pattern+Recognition&rft.atitle=Leveraging+Vector-Quantized+Variational+Autoencoder+Inner+Metrics+for+Anomaly+Detection&rft.au=Gangloff%2C+Hugo&rft.au=Pham%2C+Minh-Tan&rft.au=Courtrai%2C+Luc&rft.au=Lefevre%2C+Sebastien&rft.date=2022-08-21&rft.pub=IEEE&rft.eissn=2831-7475&rft.spage=435&rft.epage=441&rft_id=info:doi/10.1109%2FICPR56361.2022.9956102&rft.externalDocID=9956102