Abstract


= PDF Reprint,     = BibTeX entry,     = Online Abstract


Click to download BibTeX data Clik to view abstract D. Zhu, Y. Luo, L. Dai, X. Shao, L. Itti, J. Lu, Deep Salient Object Detection via Hierarchical Network Learning, In: International Conference on Neural Information Processing, Springer, pp. 319-329, Oct 2017.

Abstract: Salient object detection is a fundamental problem in both pattern recognition and image processing tasks. Previous salient object detection algorithms usually involve various features based on priors/assumptions about the properties of the objects. Inspired by the effectiveness of recently developed feature learning, we propose a novel deep salient object detection (DSOD) model using the deep residual network (ResNet 152-layers) for saliency computation. In particular, we model the image saliency from both local and global perspectives. In the local feature estimation stage, we detect local saliency by using a deep residual network (ResNet-L) which learns local region features to determine the saliency value of each pixel. In the global feature extraction stage, another deep residual network (ResNet-G) is trained to predict the saliency score of each image based on the global features. The final saliency map is generated by a conditional random field (CRF) to combining the local and global-level saliency map. Our DSOD model is capable of uniformly highlighting the objects-of-interest from complex background while well preserving object details. Quantitative and qualitative experiments on three benchmark datasets demonstrate that our DSOD method outperforms state-of-the-art methods in the salient object detection.

 

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