Data augmentation and pre-trained networks for extremely low data regimes unsupervised visual inspection

Pierre Gutierrez; Antoine Cordier; Thaïs Caldeira; Théophile Sautory

doi:10.1117/12.2591876

20 June 2021 Data augmentation and pre-trained networks for extremely low data regimes unsupervised visual inspection

Pierre Gutierrez, Antoine Cordier, Thaïs Caldeira, Théophile Sautory

Proceedings Volume 11787, Automated Visual Inspection and Machine Vision IV; 1178703 (2021) https://doi.org/10.1117/12.2591876
Event: SPIE Optical Metrology, 2021, Online Only

Abstract

The use of deep features coming from pre-trained neural networks for unsupervised anomaly detection purposes has recently gathered momentum in the computer vision field. In particular, industrial inspection applications can take advantage of such features, as demonstrated by the multiple successes of related methods on the MVTec Anomaly Detection (MVTec AD) dataset. These methods make use of neural networks pre-trained on auxiliary classification tasks such as ImageNet. However, to our knowledge, no comparative study of robustness to the low data regimes between these approaches has been conducted yet. For quality inspection applications, the handling of limited sample sizes may be crucial as large quantities of images are not available for small series. In this work, we aim to compare three approaches based on deep pre-trained features when varying the quantity of available data in MVTec AD: KNN, Mahalanobis, and PaDiM. We show that although these methods are mostly robust to small sample sizes, they still can benefit greatly from using data augmentation in the original image space, which allows to deal with very small production runs.

Conference Presentation

Citation Download Citation

Pierre Gutierrez, Antoine Cordier, Thaïs Caldeira, and Théophile Sautory "Data augmentation and pre-trained networks for extremely low data regimes unsupervised visual inspection", Proc. SPIE 11787, Automated Visual Inspection and Machine Vision IV, 1178703 (20 June 2021); https://doi.org/10.1117/12.2591876

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