.png){kind=icon}
Return
Addressing materials' microstructure diversity using transfer learning
.png){kind=icon}
OA
AI
DOI：10.1038/s41524-022-00703-z.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
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.
Journal
IF:
11.9
Papers:
2.4K
Citations:
1.7W
Organization
Cited Papers
ShareSaveDeterminants of quality of life in patients with fibromyalgia: A structural equation modeling approach.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAIShareSaveThree-diemensional materials science: An intersection of three-dimensional reconstructions and simulationsMRS BULLETINOAAI
MRS BULLETINIF4.9
OAAIShareSaveShareSaveAutomated Quantitative Analyses of Fatigue-Induced Surface Damage by Deep LearningMATERIALSOAAI
MATERIALSIF3.2
OAAIShareSave
View more