Abstract


= PDF Reprint,     = BibTeX entry,     = Online Abstract


Click to download BibTeX data Clik to view abstract D. Zhu, L. Dai, X. Shao, Q. Zhou, L. Itti, Y. Luo, J. Lu, Image salient object detection with refined deep features via convolution neural network, Journal of Electronic Imaging, Vol. 26, No. 6, p. 063018, International Society for Optics and Photonics, Nov 2017.

Abstract: Recent advances in saliency detection have used deep learning to obtain high-level features to detect salient regions. These advances have demonstrated superior results over previous works that use handcrafted low-level features for saliency detection. We propose a convolutional neural network (CNN) model to learn high-level features for saliency detection. Compared to other methods, our method presents two merits. First, when performing features extraction, apart from the convolution and pooling step in our method, we add restricted Boltzmann machine into the CNN framework to obtain more accurate features in intermediate step. Second, in order to avoid manual annotation data, we add deep belief network classifier at the end of this model to classify salient and nonsalient regions. Quantitative and qualitative experiments on three benchmark datasets demonstrate that our method performs favorably against the state-of-the-art methods.

 

Copyright © 2000-2007 by the University of Southern California, iLab and Prof. Laurent Itti.
This page generated by bibTOhtml on Fri Jan 26 09:25:23 PST 2018