@inproceedings{DurallLopezPfreundtKeuper2019,
  author    = {Ricard Durall Lopez and Franz-Josef Pfreundt and Janis Keuper},
  title     = {Object Segmentation Using Pixel-Wise Adversarial Loss},
  series = {DAGM GCPR 2019: Pattern Recognition},
  volume    = {LNCS 11824},
  publisher = {Springer},
  address   = {Cham},
  isbn      = {978-3-030-33676-9 (Online)},
  issn      = {1611-3349 (Online)},
  doi       = {10.1007/978-3-030-33676-9\_21},
  pages     = {303 -- 316},
  year      = {2019},
  abstract  = {Recent deep learning based approaches have shown remarkable success on object segmentation tasks. However, there is still room for further improvement. Inspired by generative adversarial networks, we present a generic end-to-end adversarial approach, which can be combined with a wide range of existing semantic segmentation networks to improve their segmentation performance. The key element of our method is to replace the commonly used binary adversarial loss with a high resolution pixel-wise loss. In addition, we train our generator employing stochastic weight averaging fashion, which further enhances the predicted output label maps leading to state-of-the-art results. We show, that this combination of pixel-wise adversarial training and weight averaging leads to significant and consistent gains in segmentation performance, compared to the baseline models.},
  language  = {en}
}