Addressing materials' microstructure diversity using transfer learning

no code implementations • 29 Jul 2021 • Aurèle Goetz, Ali Riza Durmaz, Martin Müller, Akhil Thomas, Dominik Britz, Pierre Kerfriden, Chris Eberl

We show that a state-of-the-art UDA approach surpasses the na\"ive application of source domain trained models on the target domain (generalization baseline) to a large extent.

Data Augmentation Domain Generalization +2