% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Trampert:891562,
      author       = {Trampert, Patrick and Rubinstein, Dmitri and Boughorbel,
                      Faysal and Schlinkmann, Christian and Luschkova, Maria and
                      Slusallek, Philipp and Dahmen, Tim and Sandfeld, Stefan},
      title        = {{D}eep {N}eural {N}etworks for {A}nalysis of {M}icroscopy
                      {I}mages—{S}ynthetic {D}ata {G}eneration and {A}daptive
                      {S}ampling},
      journal      = {Crystals},
      volume       = {11},
      number       = {3},
      issn         = {2073-4352},
      address      = {Basel},
      publisher    = {MDPI},
      reportid     = {FZJ-2021-01587},
      pages        = {258 -},
      year         = {2021},
      abstract     = {The analysis of microscopy images has always been an
                      important yet time consuming process in materials science.
                      Convolutional Neural Networks (CNNs) have been very
                      successfully used for a number of tasks, such as image
                      segmentation. However, training a CNN requires a large
                      amount of hand annotated data, which can be a problem for
                      material science data. We present a procedure to generate
                      synthetic data based on ad hoc parametric data modelling for
                      enhancing generalization of trained neural network models.
                      Especially for situations where it is not possible to gather
                      a lot of data, such an approach is beneficial and may enable
                      to train a neural network reasonably. Furthermore, we show
                      that targeted data generation by adaptively sampling the
                      parameter space of the generative models gives superior
                      results compared to generating random data points.},
      cin          = {IAS-9},
      ddc          = {540},
      cid          = {I:(DE-Juel1)IAS-9-20201008},
      pnm          = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
                      (SDLs) and Research Groups (POF4-511) / MuDiLingo - A
                      Multiscale Dislocation Language for Data-Driven Materials
                      Science (759419)},
      pid          = {G:(DE-HGF)POF4-5111 / G:(EU-Grant)759419},
      typ          = {PUB:(DE-HGF)16},
      UT           = {WOS:000633604100001},
      doi          = {10.3390/cryst11030258},
      url          = {https://juser.fz-juelich.de/record/891562},
}