Home
Uni-Logo
 

DPDB-Net: Exploiting Dense Connections for Convolutional Encoders

IEEE International Conference on Robotics and Automation (ICRA), IEEE, 2018
Abstract: Densely connected networks for classification enable feature exploration and result in state-of-the-art performance on multiple classification tasks. The alternative to dense networks is the residual network which enables feature re-usage. In this work, we combine these orthogonal concepts for encoder-decoder architectures, which we call Dual-Path Dense-Block Network (DPDB-Net). We introduce a dense block which incorporates feature re-usage and new feature exploration in the encoder. Moreover, we discuss that feature re-usage by the residual network architecture leads to a feature map explosion in the decoder and, thus, is not advantageous in this part of the network. We evaluated our proposed architecture in multiple segmentation tasks and report state-of-the-art performance on the Freiburg Forest dataset and competitive results on the CamVid dataset.
Paper

Images and movies

 

BibTex reference

@InProceedings{OB18,
  author       = "G. L. Oliveira and W. Burgard and T. Brox",
  title        = "DPDB-Net: Exploiting Dense Connections for Convolutional Encoders",
  booktitle    = "IEEE International Conference on Robotics and Automation (ICRA)",
  month        = " ",
  year         = "2018",
  publisher    = "IEEE",
  url          = "http://lmbweb.informatik.uni-freiburg.de/Publications/2018/OB18"
}

Other publications in the database