SCAI Journal Club

State-of-the-art in Domain Generalization

Speaker: Imad Eddine Ibrahim BEKKOUCH, IREMUS/STIH

Abstract:

The biggest fear when deploying machine learning models to the real world is their ability to handle new data. Domain Generalization (DG) is a field in machine learning that tries to solve the model’s dependency on the training data by leveraging many related but different data sources. This presentation will explain the problem of domain gaps and how to solve it using adversarial learning.