On the importance of visual explanation and segmentation for SAR ATR using deep learning

@article{Heiligers2018OnTI,
  title={On the importance of visual explanation and segmentation for SAR ATR using deep learning},
  author={M. J. C. Heiligers and Albert G. Huizing},
  journal={2018 IEEE Radar Conference (RadarConf18)},
  year={2018},
  pages={0394-0399}
}
After the successful application of deep learning to image classification and speech recognition in recent years, deep neural networks are now also widely used for the recognition of targets in Synthetic Aperture Radar (SAR) images. For the 10-class MSTAR SAR Automatic Target Recognition (ATR) problem, several papers have described Convolutional Neural… CONTINUE READING