Anomaly Detection Models Use Case level document

This document presents the results of several out-of-distribution data-driven detection methods, based on
neural networks, on the Safran Visual Industrial Control and Renault Welding use cases. Among these
methods, there is a new design method for improving the detection of out-of-distribution data by a neural
network using ensemble methods, and three reconstruction based methods using Normalizing Flows or Vision
Transformers.