Unrolling Loopy Top-down Semantic Feedback in Convolutional Deep Networks

Carlo Gatta, Adriana Romero, Joost van de Veijer; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2014, pp. 498-505

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.