Deep Networks for Saliency Detection via Local Estimation and Global Search

Title
Deep Networks for Saliency Detection via Local Estimation and Global Search
Authors
Yang, Ming-hsuan
Keywords
Estimation; Image color analysis; Training; Feature extraction; Neural networks; Search problems; Accuracy
Issue Date
2015-06
Publisher
IEEE
Citation
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 3183-3192
Abstract
This paper presents a saliency detection algorithm by integrating both local estimation and global search. In the local estimation stage, we detect local saliency by using a deep neural network (DNN-L) which learns local patch features to determine the saliency value of each pixel. The estimated local saliency maps are further refined by exploring the high level object concept. In the global search stage, the local saliency map together with global contrast and geometric information are used as global features to describe a set of object candidate regions. Another deep neural network (DNN-G) is trained to predict the saliency score of each object region based on the global features. The final saliency map is generated by a weighted sum of salient object regions. Our method presents two interesting insights. First, local features learned by a supervised scheme can effectively capture local contrast, texture and shape information for saliency detection. Second, complex relationship between different global saliency cues can be captured by deep networks and exploited principally rather than heuristically. Quantitative and qualitative experiments on large benchmark data sets demonstrate that our algorithm performs favorably against the state-of-the-art methods.
URI
http://www.cv-foundation.org/openaccess/content_cvpr_2015/html/Wang_Deep_Networks_for_2015_CVPR_paper.htmlhttp://hdl.handle.net/20.500.11754/25604
ISBN
978-1-4673-6964-0
ISSN
1063-6919; 1063-6919
DOI
http://dx.doi.org/10.1109/CVPR.2015.7298938
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE AND ENGINEERING(컴퓨터공학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE