Joint Use of Skip Connections and Synthetic Corruption for Anomaly Detection with Autoencoders

Anne-Sophie Collin () and Christophe Vleeschouwer ()
Additional contact information
Anne-Sophie Collin: UCLouvain
Christophe Vleeschouwer: UCLouvain

A chapter in Control Charts and Machine Learning for Anomaly Detection in Manufacturing, 2022, pp 187-215 from Springer

Abstract: Abstract In industrial vision, the anomaly detection problem can be addressed with an autoencoder trained to map an arbitrary image, i.e. with or without any defect, to a clean image, i.e. without any defect. In this approach, anomaly detection relies conventionally on the reconstruction residual or, alternatively, on the reconstruction uncertainty. To improve the sharpness of the reconstruction, we consider an autoencoder architecture with skip connections. In the common scenario where only clean images are available for training, we propose to corrupt them with a synthetic noise model to prevent the convergence of the network towards the identity mapping, and introduce an original Stain noise model for that purpose. We show that this model favors the reconstruction of clean images from arbitrary real-world images, regardless of the actual defects appearance. In addition to demonstrating the relevance of our approach, our validation provides the first consistent assessment of reconstruction-based methods, by comparing their performance over the MVTec AD dataset [1], both for pixel- and image-wise anomaly detection. Our implementation is available at https://github.com/anncollin/AnomalyDetection-Keras .

Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:ssrchp:978-3-030-83819-5_8

Ordering information: This item can be ordered from
http://www.springer.com/9783030838195

DOI: 10.1007/978-3-030-83819-5_8

Access Statistics for this chapter

More chapters in Springer Series in Reliability Engineering from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().