% 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{Lange:851272,
      author       = {Lange, Julius and Cavallaro, Gabriele and Götz, Markus and
                      Ernir, Erlingsson and Riedel, Morris},
      title        = {{T}he {I}nfluence of {S}ampling {M}ethods on {P}ixel-{W}ise
                      {H}yperspectral {I}mage {C}lassification with 3{D}
                      {C}onvolutional {N}eural {N}etworks},
      reportid     = {FZJ-2018-04967},
      pages        = {2087 - 2090},
      year         = {2018},
      comment      = {IGARSS 2018 - 2018 IEEE International Geoscience and Remote
                      Sensing Symposium},
      booktitle     = {IGARSS 2018 - 2018 IEEE International
                       Geoscience and Remote Sensing
                       Symposium},
      abstract     = {Supervised image classification is one of the essential
                      techniques for generating semantic maps from remotely sensed
                      images.The lack of labeled ground truth datasets, due to the
                      inherent time effort and cost involved in collecting
                      training samples, has led to the practice of training and
                      validating new classifiers within a single image. In line
                      with that, the dominant approach for the division of the
                      available ground truth into disjoint training and test sets
                      is random sampling. This paper discusses the problems that
                      arise when this strategy is adopted in conjunction with
                      spectral-spatial and pixel-wise classifiers such as 3D
                      Convolutional Neural Networks (3D CNN). It is shown that a
                      random sampling scheme leads to a violation of the
                      independence assumption and to the illusion that global
                      knowledge is extracted from the training set.To tackle this
                      issue, two improved sampling strategies based on the
                      Density-Based Clustering Algorithm (DBSCAN) are proposed.
                      They minimize the violation of the train and test samples
                      independence assumption and thus ensure an honest estimation
                      of the generalization capabilities of the classifier.},
      month         = {Jul},
      date          = {2018-07-22},
      organization  = {IEEE International Geoscience and
                       Remote Sensing Symposium (IGARSS),
                       Valencia (Spain), 22 Jul 2018 - 27 Jul
                       2018},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {512 - Data-Intensive Science and Federated Computing
                      (POF3-512) / DEEP-EST - DEEP - Extreme Scale Technologies
                      (754304) / SIMDAS - Upgrade of CaSToRC into a Center of
                      Excellence in Simulation and Data Science (763558)},
      pid          = {G:(DE-HGF)POF3-512 / G:(EU-Grant)754304 /
                      G:(EU-Grant)763558},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      doi          = {10.1109/IGARSS.2018.8518671},
      url          = {https://juser.fz-juelich.de/record/851272},
}