FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3186538852> ?p ?o ?g. }

• W3186538852 abstract "Materials' microstructures are signatures of their alloying composition and processing history. Therefore, microstructures exist in a wide variety. As materials become increasingly complex to comply with engineering demands, advanced computer vision (CV) approaches such as deep learning (DL) inevitably gain relevance for quantifying microstrucutures' constituents from micrographs. While DL can outperform classical CV techniques for many tasks, shortcomings are poor data efficiency and generalizability across datasets. This is inherently in conflict with the expense associated with annotating materials data through experts and extensive materials diversity. To tackle poor domain generalizability and the lack of labeled data simultaneously, we propose to apply a sub-class of transfer learning methods called unsupervised domain adaptation (UDA). These algorithms address the task of finding domain-invariant features when supplied with annotated source data and unannotated target data, such that performance on the latter distribution is optimized despite the absence of annotations. Exemplarily, this study is conducted on a lath-shaped bainite segmentation task in complex phase steel micrographs. Here, the domains to bridge are selected to be different metallographic specimen preparations (surface etchings) and distinct imaging modalities. We show that a state-of-the-art UDA approach surpasses the naive application of source domain trained models on the target domain (generalization baseline) to a large extent. This holds true independent of the domain shift, despite using little data, and even when the baseline models were pre-trained or employed data augmentation. Through UDA, mIoU was improved over generalization baselines from 82.2%, 61.0%, 49.7% to 84.7%, 67.3%, 73.3% on three target datasets, respectively. This underlines this techniques' potential to cope with materials variance." @default.
• W3186538852 created "2021-08-02" @default.
• W3186538852 creator A5014068361 @default.
• W3186538852 creator A5014555327 @default.
• W3186538852 creator A5014591833 @default.
• W3186538852 creator A5034000864 @default.
• W3186538852 creator A5068401743 @default.
• W3186538852 creator A5079132819 @default.
• W3186538852 creator A5090182937 @default.
• W3186538852 date "2021-07-29" @default.
• W3186538852 modified "2023-09-27" @default.
• W3186538852 title "Addressing materials' microstructure diversity using transfer learning." @default.
• W3186538852 cites W1668901377 @default.
• W3186538852 cites W1861492603 @default.
• W3186538852 cites W1901129140 @default.
• W3186538852 cites W1983665697 @default.
• W3186538852 cites W2031342017 @default.
• W3186538852 cites W2340897893 @default.
• W3186538852 cites W2346062110 @default.
• W3186538852 cites W2431874326 @default.
• W3186538852 cites W2556967412 @default.
• W3186538852 cites W2883386984 @default.
• W3186538852 cites W2889396403 @default.
• W3186538852 cites W2896966666 @default.
• W3186538852 cites W2925047705 @default.
• W3186538852 cites W2949650786 @default.
• W3186538852 cites W2949667497 @default.
• W3186538852 cites W2952787450 @default.
• W3186538852 cites W2952865063 @default.
• W3186538852 cites W2962835968 @default.
• W3186538852 cites W2962837118 @default.
• W3186538852 cites W2962858109 @default.
• W3186538852 cites W2963073217 @default.
• W3186538852 cites W2963107255 @default.
• W3186538852 cites W2963486920 @default.
• W3186538852 cites W2963826681 @default.
• W3186538852 cites W2970140852 @default.
• W3186538852 cites W2978753875 @default.
• W3186538852 cites W2991391304 @default.
• W3186538852 cites W3015884347 @default.
• W3186538852 cites W3042258452 @default.
• W3186538852 cites W3043892742 @default.
• W3186538852 cites W3090747900 @default.
• W3186538852 cites W3095828720 @default.
• W3186538852 cites W3100230575 @default.
• W3186538852 cites W3156693589 @default.
• W3186538852 cites W3164411016 @default.
• W3186538852 cites W3173206925 @default.
• W3186538852 cites W3016625911 @default.
• W3186538852 hasPublicationYear "2021" @default.
• W3186538852 type Work @default.
• W3186538852 sameAs 3186538852 @default.
• W3186538852 citedByCount "0" @default.
• W3186538852 crossrefType "posted-content" @default.
• W3186538852 hasAuthorship W3186538852A5014068361 @default.
• W3186538852 hasAuthorship W3186538852A5014555327 @default.
• W3186538852 hasAuthorship W3186538852A5014591833 @default.
• W3186538852 hasAuthorship W3186538852A5034000864 @default.
• W3186538852 hasAuthorship W3186538852A5068401743 @default.
• W3186538852 hasAuthorship W3186538852A5079132819 @default.
• W3186538852 hasAuthorship W3186538852A5090182937 @default.
• W3186538852 hasConcept C105795698 @default.
• W3186538852 hasConcept C108583219 @default.
• W3186538852 hasConcept C111368507 @default.
• W3186538852 hasConcept C119857082 @default.
• W3186538852 hasConcept C12725497 @default.
• W3186538852 hasConcept C127313418 @default.
• W3186538852 hasConcept C127413603 @default.
• W3186538852 hasConcept C134306372 @default.
• W3186538852 hasConcept C150899416 @default.
• W3186538852 hasConcept C153180895 @default.
• W3186538852 hasConcept C154945302 @default.
• W3186538852 hasConcept C177148314 @default.
• W3186538852 hasConcept C201995342 @default.
• W3186538852 hasConcept C27158222 @default.
• W3186538852 hasConcept C2780451532 @default.
• W3186538852 hasConcept C33923547 @default.
• W3186538852 hasConcept C36503486 @default.
• W3186538852 hasConcept C41008148 @default.
• W3186538852 hasConcept C89600930 @default.
• W3186538852 hasConcept C97931131 @default.
• W3186538852 hasConceptScore W3186538852C105795698 @default.
• W3186538852 hasConceptScore W3186538852C108583219 @default.
• W3186538852 hasConceptScore W3186538852C111368507 @default.
• W3186538852 hasConceptScore W3186538852C119857082 @default.
• W3186538852 hasConceptScore W3186538852C12725497 @default.
• W3186538852 hasConceptScore W3186538852C127313418 @default.
• W3186538852 hasConceptScore W3186538852C127413603 @default.
• W3186538852 hasConceptScore W3186538852C134306372 @default.
• W3186538852 hasConceptScore W3186538852C150899416 @default.
• W3186538852 hasConceptScore W3186538852C153180895 @default.
• W3186538852 hasConceptScore W3186538852C154945302 @default.
• W3186538852 hasConceptScore W3186538852C177148314 @default.
• W3186538852 hasConceptScore W3186538852C201995342 @default.
• W3186538852 hasConceptScore W3186538852C27158222 @default.
• W3186538852 hasConceptScore W3186538852C2780451532 @default.
• W3186538852 hasConceptScore W3186538852C33923547 @default.
• W3186538852 hasConceptScore W3186538852C36503486 @default.
• W3186538852 hasConceptScore W3186538852C41008148 @default.
• W3186538852 hasConceptScore W3186538852C89600930 @default.

• next