Salient Object Detection via Bootstrap Learning

Title
Salient Object Detection via Bootstrap Learning
Authors
Yang, Ming-hsuan
Keywords
Training; Kernel; Computational modeling; Feature extraction; Object detection; Boosting; Support vector machines
Issue Date
2015-06
Publisher
IEEE
Citation
Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on 2015 June, Page. 1884-1892
Abstract
We propose a bootstrap learning algorithm for salient object detection in which both weak and strong models are exploited. First, a weak saliency map is constructed based on image priors to generate training samples for a strong model. Second, a strong classifier based on samples directly from an input image is learned to detect salient pixels. Results from multiscale saliency maps are integrated to further improve the detection performance. Extensive experiments on six benchmark datasets demonstrate that the proposed bootstrap learning algorithm performs favorably against the state-of-the-art saliency detection methods. Furthermore, we show that the proposed bootstrap learning approach can be easily applied to other bottom-up saliency models for significant improvement.
URI
http://ieeexplore.ieee.org/document/7298798/?isnumber=7298593&arnumber=7298798http://hdl.handle.net/20.500.11754/25603
ISBN
978-1-4673-6964-0
ISSN
1063-6919; 1063-6919
DOI
http://dx.doi.org/10.1109/CVPR.2015.7298798
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > DIVISION OF COMPUTER SCIENCES 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