Attention-Aware Generative Adversarial Networks (ATA-GANs)

  title={Attention-Aware Generative Adversarial Networks (ATA-GANs)},
  author={Dimitris Kastaniotis and Ioanna Ntinou and Dimitrios Tsourounis and George Economou and Spiros Fotopoulos},
  journal={2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP)},
In this work, we present a novel approach for training Generative Adversarial Networks (GANs). Using the attention maps produced by a Teacher Network we are able to improve the quality of the generated images as well as perform weakly supervised object localization on the generated images. To this end, we generate images of HEp-2 cells captured with Indirect Imunofluoresence (IIF) and study the ability of our network to perform a weakly localization of the cell. First, we demonstrate that… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 11 times over the past 90 days. VIEW TWEETS