Salient object detection via bootstrap learning

Na Tong; Huchuan Lu; Xiang Ruan; Ming Hsuan Yang

doi:10.1109/CVPR.2015.7298798

Salient object detection via bootstrap learning

Na Tong, Huchuan Lu, Xiang Ruan, Ming Hsuan Yang

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

276 Citations (Scopus)

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.

Original language	English
Title of host publication	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Publisher	IEEE Computer Society
Pages	1884-1892
Number of pages	9
ISBN (Electronic)	9781467369640
DOIs	https://doi.org/10.1109/CVPR.2015.7298798
Publication status	Published - 2015 Oct 14
Event	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States Duration: 2015 Jun 7 → 2015 Jun 12

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	07-12-June-2015
ISSN (Print)	1063-6919

Other

Other	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Country/Territory	United States
City	Boston
Period	15/6/7 → 15/6/12

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

All Science Journal Classification (ASJC) codes

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2015.7298798

Cite this

Tong, N., Lu, H., Ruan, X., & Yang, M. H. (2015). Salient object detection via bootstrap learning. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 (pp. 1884-1892). [7298798] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015). IEEE Computer Society. https://doi.org/10.1109/CVPR.2015.7298798

@inproceedings{32118289ce7743e9967d54c1c3d1a55e,

title = "Salient object detection via bootstrap learning",

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.",

author = "Na Tong and Huchuan Lu and Xiang Ruan and Yang, {Ming Hsuan}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 ; Conference date: 07-06-2015 Through 12-06-2015",

year = "2015",

month = oct,

day = "14",

doi = "10.1109/CVPR.2015.7298798",

language = "English",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "1884--1892",

booktitle = "IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015",

address = "United States",

}

Tong, N, Lu, H, Ruan, X & Yang, MH 2015, Salient object detection via bootstrap learning. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015., 7298798, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07-12-June-2015, IEEE Computer Society, pp. 1884-1892, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 15/6/7. https://doi.org/10.1109/CVPR.2015.7298798

Salient object detection via bootstrap learning. / Tong, Na; Lu, Huchuan; Ruan, Xiang; Yang, Ming Hsuan.

IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. p. 1884-1892 7298798 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Salient object detection via bootstrap learning

AU - Tong, Na

AU - Lu, Huchuan

AU - Ruan, Xiang

AU - Yang, Ming Hsuan

PY - 2015/10/14

Y1 - 2015/10/14

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84959240205&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959240205&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2015.7298798

DO - 10.1109/CVPR.2015.7298798

M3 - Conference contribution

AN - SCOPUS:84959240205

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 1884

EP - 1892

BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

PB - IEEE Computer Society

T2 - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

Y2 - 7 June 2015 through 12 June 2015

ER -

Salient object detection via bootstrap learning

Abstract

Publication series

Other

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this