Hierarchical Recurrent Filtering for Fully Convolutional DenseNets

Jörg Wagner, Volker Fischer, Michael Herman, Sven Behnke

European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 2018, Bruges, Belgium, April 25 – 27, 2018

Abstract:

Generating a robust representation of the environment is a crucial ability of learning agents. Deep learning based methods have greatly improved perception systems but still fail in challenging situations. These failures are often not solvable on the basis of a single image. In this work, we present a parameter-efficient temporal filtering concept which extends an existing single-frame segmentation model to work with multiple frames. The resulting recurrent architecture temporally filters representations on all abstraction levels in a hierarchical manner, while decoupling temporal dependencies from scene representation. Using a synthetic dataset, we show the ability of our model to cope with data perturbations and highlight the importance of recurrent and hierarchical filtering.

PDF Bibtex

@INPROCEEDINGS{Wagner2018ESANN,
  author={Jörg Wagner and Volker Fischer and Michael Herman and Sven Behnke},
  booktitle={26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)},
  title={Hierarchical Recurrent Filtering for Fully Convolutional DenseNets},
  year={2018},
  month={April},
}