Skip to main navigation Skip to search Skip to main content

Unsupervised Variability Normalization For Anomaly Detection

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

Abstract

Anomaly detectors are necessary to automatize industrial quality control. However, crafting such detectors is difficult due to the complexity and variability of the object even when working only with rigid objects. We show that adding a deep learning normalization step as a preprocessing step to model based detectors allows for better and more robust detections. This self-supervised normalization neural network is trained on non-anomalous data only. The proposed preprocessing method, followed by an automatic detector, achieves state-of-the-art results on rigid objects from the MvTec dataset.
Original languageEnglish
Title of host publication2021 IEEE International Conference on Image Processing, ICIP 2021, Proceedings
PublisherIEEE
Pages989-993
Number of pages5
ISBN (Electronic)9781665441155
ISBN (Print)9781665431026
DOIs
Publication statusPublished - 2021
Externally publishedYes
Event2021 IEEE International Conference on Image Processing - Anchorage, United States
Duration: 19 Sept 202122 Sept 2021

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2021-September
ISSN (Print)1522-4880

Conference

Conference2021 IEEE International Conference on Image Processing
Country/TerritoryUnited States
CityAnchorage
Period19/09/2122/09/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Funding

Work supported by a CIFRE scholarship of the French Ministry for Higher Studies, Research and Innovation.

Keywords

  • Anomaly detection
  • Deep-learning
  • Denoising
  • Self-similarity

Fingerprint

Dive into the research topics of 'Unsupervised Variability Normalization For Anomaly Detection'. Together they form a unique fingerprint.

Cite this