Insights of anomaly detection: How does polluted training data influence performance?

Jan Lehr; Martin Pape; Samuel Günther; Jörg Krüger

doi:10.1117/12.3023184

3 April 2024 Insights of anomaly detection: How does polluted training data influence performance?

Jan Lehr, Martin Pape, Samuel Günther, Jörg Krüger

Proceedings Volume 13072, Sixteenth International Conference on Machine Vision (ICMV 2023); 1307217 (2024) https://doi.org/10.1117/12.3023184
Event: Sixteenth International Conference on Machine Vision (ICMV 2023), 2023, Yerevan, Armenia

Abstract

Anomaly detection is one of the most popular fields for computer vision in industrial applications. The idea of training machine learning only on defect-free objects saves enormous amounts of integration effort. The state of the art shows that current methods on public data sets (e.g. MVTec AD data set [1]) have already solved the problem with AUROC segmentation scores of more than 99%. In real-world applications training data is not as ”clean” as in public data sets. This work investigates the changes in detection performance when outliers end up in the training data. For this purpose, the training data is enriched step by step with images of defective objects. The AUROC score and the anomaly score is used as a quality criterion for performance measurement. We show that state of the art methods can be very robust, but that in some scenarios a draw down of 15 percentage points is possible.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jan Lehr, Martin Pape, Samuel Günther, and Jörg Krüger "Insights of anomaly detection: How does polluted training data influence performance?", Proc. SPIE 13072, Sixteenth International Conference on Machine Vision (ICMV 2023), 1307217 (3 April 2024); https://doi.org/10.1117/12.3023184

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available