% 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{Kazimi:1030713,
      author       = {Kazimi, Bashir and Sandfeld, Stefan},
      title        = {{E}nhancing {S}emantic {S}egmentation in
                      {H}igh-{R}esolution {TEM} {I}mages: {A} {C}omparative
                      {S}tudy of {B}atch {N}ormalization and {I}nstance
                      {N}ormalization},
      journal      = {Microscopy and microanalysis},
      volume       = {31},
      number       = {1},
      issn         = {1079-8501},
      address      = {Oxford},
      publisher    = {Oxford University Press},
      reportid     = {FZJ-2024-05420},
      pages        = {ozae093},
      year         = {2025},
      abstract     = {Integrating deep learning into image analysis for
                      transmission electron microscopy (TEM) holds significant
                      promise for advancing materials science and nanotechnology.
                      Deep learning is able to enhance image quality, to automate
                      feature detection, and to accelerate data analysis,
                      addressing the complex nature of TEM datasets. This
                      capability is crucial for precise and efficient
                      characterization of details on the nano—and microscale,
                      e.g., facilitating more accurate and high-throughput
                      analysis of nanoparticle structures. This study investigates
                      the influence of batch normalization (BN) and instance
                      normalization (IN) on the performance of deep learning
                      models for semantic segmentation of high-resolution TEM
                      images. Using U-Net and ResNet architectures, we trained
                      models on two different datasets. Our results demonstrate
                      that IN consistently outperforms BN, yielding higher Dice
                      scores and Intersection over Union metrics. These findings
                      underscore the necessity of selecting appropriate
                      normalization methods to maximize the performance of deep
                      learning models applied to TEM images.},
      cin          = {IAS-9},
      ddc          = {500},
      cid          = {I:(DE-Juel1)IAS-9-20201008},
      pnm          = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
                      (SDLs) and Research Groups (POF4-511)},
      pid          = {G:(DE-HGF)POF4-5111},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {39405188},
      UT           = {WOS:001332600800001},
      doi          = {10.1093/mam/ozae093},
      url          = {https://juser.fz-juelich.de/record/1030713},
}