% 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”.

@MASTERSTHESIS{Kromm:1046025,
      author       = {Kromm, Edward},
      othercontributors = {Benassou, Sabrina and Kesselheim, Stefan},
      title        = {{D}ata {F}usion for {S}cene {G}raph {G}eneration:
                      {B}ridging {S}imulated and {R}eal-{W}orld {D}atasets},
      school       = {Hochschule Coburg},
      type         = {Masterarbeit},
      address      = {Jülich},
      reportid     = {FZJ-2025-03665},
      pages        = {102 pages: Figures, Tables},
      year         = {2025},
      note         = {Masterarbeit, Hochschule Coburg, 2025},
      abstract     = {Scene graph generation has emerged as a powerful tool for
                      AI-driven visual understandingof images by not only
                      detecting objects in an image but also predicting the
                      relationshipsbetween them, such as car–stops at–traffic
                      light or pedestrian–crosses–street. This capabilityis
                      particularly important for autonomous driving, where
                      relational context between roadusers and infrastructure
                      plays a critical role. However, the application of scene
                      graphgeneration in this domain is hindered by the scarcity
                      of annotated datasets. Drivingsimulators such as CARLA
                      provide a scalable alternative, enabling efficient data
                      generationcompared to manual annotation. Yet models trained
                      exclusively on simulated data oftenfail to generalize to
                      real-world data due to the substantial domain gap between
                      the two.This thesis addresses this challenge by proposing a
                      novel data fusion framework thatcombines simulated and real
                      datasets to construct autonomous driving–specific
                      relationshipannotations and subsequently bridge the domain
                      gap for real-world prediction. The workpresents the complete
                      pipeline, including dataset generation in simulation,
                      adaptationof publicly available resources, and augmentation
                      strategies. The Relation Transformermodel is analyzed in
                      depth, and particular attention is given to interpreting its
                      internalmechanisms by visualizing the learned attention maps
                      as heatmaps. This analysis providesinsights into whether the
                      model focuses on semantically meaningful regions when
                      predictingrelationships. Building on this understanding, two
                      new approaches are introduced to enableinference on real
                      data while transferring relational knowledge acquired in
                      simulation. Anablation study further quantifies the impact
                      of the domain gap on model performance andhighlights the
                      strengths and limitations of the proposed methods. Results
                      demonstratethat one of the developed approaches effectively
                      mitigates the simulation-to-reality gapand concrete
                      suggestions for advancing this technique toward further uses
                      for AI-drivenvisual understanding of images in the
                      automotive context are provided.},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
                      and Research Groups (POF4-511) / nxtAIM - nxtAIM – NXT GEN
                      AI Methods (19A23014l)},
      pid          = {G:(DE-HGF)POF4-5112 / G:(BMWK)19A23014l},
      typ          = {PUB:(DE-HGF)19},
      doi          = {10.34734/FZJ-2025-03665},
      url          = {https://juser.fz-juelich.de/record/1046025},
}