%0 Conference Proceedings
%T Unrolling loopy top-down semantic feedback in convolutional deep networks
%A Carlo Gatta
%A Adriana Romero
%A Joost Van de Weijer
%B Workshop on Deep Vision: Deep Learning for Computer Vision
%D 2014
%F Carlo Gatta2014
%O LAMP; MILAB; 601.160; 600.079
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2490), last updated on Fri, 04 Feb 2022 13:11:34 +0100
%X In this paper, we propose a novel way to perform top-down semantic feedback in convolutional deep networks for efficient and accurate image parsing. We also show how to add global appearance/semantic features, which have shown to improve image parsing performance in state-of-the-art methods, and was not present in previous convolutional approaches. The proposed method is characterised by an efficient training and a sufficiently fast testing. We use the well known SIFTflow dataset to numerically show the advantages provided by our contributions, and to compare with state-of-the-art image parsing convolutional based approaches.
%U http://refbase.cvc.uab.es/files/GRW2014.pdf
%U http://dx.doi.org/10.1109/CVPRW.2014.80
%P 498-505