Group Saliency Propagation for large scale and quick image co-segmentation

Koteswar Rao Jerripothula; Jianfei Cai; Junsong Yuan

doi:10.1109/ICIP.2015.7351686

Group Saliency Propagation for large scale and quick image co-segmentation

Koteswar Rao Jerripothula, Jianfei Cai, Junsong Yuan

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

17 Citations (Scopus)

Abstract

Most of the existing co-segmentation methods are usually complex, and require pre-grouping of images, fine-tuning a few parameters and initial segmentation masks etc. These limitations become serious concerns for their application on large scale datasets. In this paper, Group Saliency Propagation (GSP) model is proposed where a single group saliency map is developed, which can be propagated to segment the entire group. In addition, it is also shown how a pool of these group saliency maps can help in quickly segmenting new input images. Experiments demonstrate that the proposed method can achieve competitive performance on several benchmark co-segmentation datasets including ImageNet, with the added advantage of speed up.

Original language	English
Title of host publication	2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
Editors	Jean-Philippe Thiran, Fabrice Labeau
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	4639-4643
Number of pages	5
ISBN (Electronic)	9781479983391, 9781479983384
DOIs	https://doi.org/10.1109/ICIP.2015.7351686
Publication status	Published - 2015
Externally published	Yes
Event	IEEE International Conference on Image Processing 2015 - Quebec City, Canada Duration: 27 Sept 2015 → 30 Sept 2015 Conference number: 22nd http://icip2015.org/index.html https://ieeexplore.ieee.org/xpl/conhome/7328364/proceeding (Proceedings)

Conference

Conference	IEEE International Conference on Image Processing 2015
Abbreviated title	ICIP 2015
Country/Territory	Canada
City	Quebec City
Period	27/09/15 → 30/09/15
Internet address	http://icip2015.org/index.html https://ieeexplore.ieee.org/xpl/conhome/7328364/proceeding (Proceedings)

Keywords

co-segmentation
fusion
group
ImageNet
large scale
propagation
quick

Access to Document

10.1109/ICIP.2015.7351686

Cite this

@inproceedings{7ef33496049a4ab89d4e4f0f312b564a,

title = "Group Saliency Propagation for large scale and quick image co-segmentation",

abstract = "Most of the existing co-segmentation methods are usually complex, and require pre-grouping of images, fine-tuning a few parameters and initial segmentation masks etc. These limitations become serious concerns for their application on large scale datasets. In this paper, Group Saliency Propagation (GSP) model is proposed where a single group saliency map is developed, which can be propagated to segment the entire group. In addition, it is also shown how a pool of these group saliency maps can help in quickly segmenting new input images. Experiments demonstrate that the proposed method can achieve competitive performance on several benchmark co-segmentation datasets including ImageNet, with the added advantage of speed up.",

keywords = "co-segmentation, fusion, group, ImageNet, large scale, propagation, quick",

author = "Jerripothula, {Koteswar Rao} and Jianfei Cai and Junsong Yuan",

year = "2015",

doi = "10.1109/ICIP.2015.7351686",

language = "English",

pages = "4639--4643",

editor = "Thiran, {Jean-Philippe } and Fabrice Labeau",

booktitle = "2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "IEEE International Conference on Image Processing 2015, ICIP 2015 ; Conference date: 27-09-2015 Through 30-09-2015",

url = "http://icip2015.org/index.html, https://ieeexplore.ieee.org/xpl/conhome/7328364/proceeding",

}

Jerripothula, KR, Cai, J & Yuan, J 2015, Group Saliency Propagation for large scale and quick image co-segmentation. in J-P Thiran & F Labeau (eds), 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 4639-4643, IEEE International Conference on Image Processing 2015, Quebec City, Quebec, Canada, 27/09/15. https://doi.org/10.1109/ICIP.2015.7351686

Group Saliency Propagation for large scale and quick image co-segmentation. / Jerripothula, Koteswar Rao; Cai, Jianfei; Yuan, Junsong.
2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings. ed. / Jean-Philippe Thiran; Fabrice Labeau. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 4639-4643.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Group Saliency Propagation for large scale and quick image co-segmentation

AU - Jerripothula, Koteswar Rao

AU - Cai, Jianfei

AU - Yuan, Junsong

N1 - Conference code: 22nd

PY - 2015

Y1 - 2015

N2 - Most of the existing co-segmentation methods are usually complex, and require pre-grouping of images, fine-tuning a few parameters and initial segmentation masks etc. These limitations become serious concerns for their application on large scale datasets. In this paper, Group Saliency Propagation (GSP) model is proposed where a single group saliency map is developed, which can be propagated to segment the entire group. In addition, it is also shown how a pool of these group saliency maps can help in quickly segmenting new input images. Experiments demonstrate that the proposed method can achieve competitive performance on several benchmark co-segmentation datasets including ImageNet, with the added advantage of speed up.

AB - Most of the existing co-segmentation methods are usually complex, and require pre-grouping of images, fine-tuning a few parameters and initial segmentation masks etc. These limitations become serious concerns for their application on large scale datasets. In this paper, Group Saliency Propagation (GSP) model is proposed where a single group saliency map is developed, which can be propagated to segment the entire group. In addition, it is also shown how a pool of these group saliency maps can help in quickly segmenting new input images. Experiments demonstrate that the proposed method can achieve competitive performance on several benchmark co-segmentation datasets including ImageNet, with the added advantage of speed up.

KW - co-segmentation

KW - fusion

KW - group

KW - ImageNet

KW - large scale

KW - propagation

KW - quick

UR - http://www.scopus.com/inward/record.url?scp=84956615581&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2015.7351686

DO - 10.1109/ICIP.2015.7351686

M3 - Conference Paper

AN - SCOPUS:84956615581

SP - 4639

EP - 4643

BT - 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings

A2 - Thiran, Jean-Philippe

A2 - Labeau, Fabrice

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

T2 - IEEE International Conference on Image Processing 2015

Y2 - 27 September 2015 through 30 September 2015

ER -

Group Saliency Propagation for large scale and quick image co-segmentation

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this