Open access
Aug 2026
Self-Supervised Feature Extraction for Domain-Specific Anomaly Detection with Normalizing Flows
This work investigates the use of a self-supervised feature extractor —a Masked Autoencoder (MAE)— to learn domain-specific features when the application domain differs significantly from ImageNet, and compute the resulting anomaly maps for each of them on concrete datasets.
Thibault Richard, Bruno Galerne, Y. Gousseau et al.
· e-Journal of Nondestructive... · 0 citations