Efficient Convolutional Patch Networks for Scene Understanding
Computer Vision Group, Friedrich Schiller University of Jena, Jena, Germany
SUNw: Scene Understanding Workshop, 2015
@article{brust2015efficient,
title={Efficient Convolutional Patch Networks for Scene Understanding},
author={Brust, Clemens-Alexander and Sickert, Sven and Simon, Marcel and Rodner, Erik and Denzler, Joachim},
year={2015}
}
In this paper, we present convolutional patch networks, which are convolutional (neural) networks (CNN) learned to distinguish different image patches and which can be used for pixel-wise labeling. We show how to easily learn spatial priors for certain categories jointly with their appearance. Experiments for urban scene understanding demonstrate state-of-the-art results on the LabelMeFacade dataset. Our approach is implemented as a new CNN framework especially designed for semantic segmentation with fully-convolutional architectures.
July 24, 2015 by hgpu
