% 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”.

@INPROCEEDINGS{DelBue:1050636,
      author       = {Emam, Ahmed and Farag, Mohamed and Kierdorf, Jana and
                      Klingbeil, Lasse and Rascher, Uwe and Roscher, Ribana},
      editor       = {Del Bue, Alessio and Canton, Cristian and Pont-Tuset, Jordi
                      and Tommasi, Tatiana},
      title        = {{A} {F}ramework for {E}nhanced {D}ecision {S}upport
                      in {D}igital {A}griculture {U}sing {E}xplainable {M}achine
                      {L}earning},
      volume       = {15625},
      address      = {Cham},
      publisher    = {Springer Nature Switzerland},
      reportid     = {FZJ-2026-00388},
      isbn         = {978-3-031-91834-6 (print)},
      series       = {Lecture Notes in Computer Science},
      pages        = {31 - 45},
      year         = {2025},
      abstract     = {Model explainability, which integrates interpretability
                      with domain knowledge, is crucial for assessing the
                      reliability of machine learning frameworks, particularly in
                      enhancing decision support in digital agriculture. Efforts
                      have been made to establish a clear definition of
                      explainability and develop new interpretability techniques.
                      Assessing interpretability is essential to fully harness the
                      potential of explainability. In this paper, we compare
                      Gradient-weighted Class Activation Mapping, an
                      interpretability technique for Convolutional Neural
                      Networks, with Raw Attentions for Vision Transformers. We
                      analyze both methods in an image-based task to classify the
                      harvest-readiness of cauliflower plants. By developing a
                      model-agnostic framework to compare models based on
                      explainability, we pave the way for more reliable digital
                      agriculture systems.},
      month         = {Sep},
      date          = {2024-09-29},
      organization  = {Computer Vision – ECCV 2024
                       Workshop, Milan (Italy), 29 Sep 2024 -
                       4 Oct 2024},
      cin          = {IBG-2},
      cid          = {I:(DE-Juel1)IBG-2-20101118},
      pnm          = {2173 - Agro-biogeosystems: controls, feedbacks and impact
                      (POF4-217)},
      pid          = {G:(DE-HGF)POF4-2173},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      doi          = {10.1007/978-3-031-91835-3_3},
      url          = {https://juser.fz-juelich.de/record/1050636},
}