Addressing materials' microstructure diversity using transfer learning

doi:10.1038/s41524-022-00703-z

Addressing materials' microstructure diversity using transfer learning

2022-02-03

22

OA

AI

DOI：10.1038/s41524-022-00703-z

Original

Original request for help

Save

Abstract

En 中文

Materials' microstructures are signatures of their alloying composition and processing history. Automated, quantitative analyses of microstructural constituents were lately accomplished through deep learning approaches. However, their shortcomings are poor data efficiency and domain generalizability across data sets, inherently conflicting the expenses associated with annotating data through experts, and extensive materials diversity. To tackle both, we propose to apply a sub-class of transfer learning methods called unsupervised domain adaptation (UDA). UDA addresses the task of finding domain-invariant features when supplied with annotated source data and unannotated target data, such that performance on the latter is optimized. Exemplarily, this study is conducted on a lath-shaped bainite segmentation task in complex phase steel micrographs. Domains to bridge are selected to be different metallographic specimen preparations and distinct imaging modalities. We show that a state-of-the-art UDA approach substantially fosters the transfer between the investigated domains, underlining this technique's potential to cope with materials variance.

Addressing materials' microstructure diversity using transfer learning

Abstract

Journal

Organization