An exemplar-based CRF for multi-instance object segmentation

Xuming He; Stephen Gould

doi:10.1109/CVPR.2014.45

An exemplar-based CRF for multi-instance object segmentation

Xuming He^*, Stephen Gould

^*Corresponding author for this work

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

44 Citations (Scopus)

Abstract

We address the problem of joint detection and segmentation of multiple object instances in an image, a key step towards scene understanding. Inspired by data-driven methods, we propose an exemplar-based approach to the task of instance segmentation, in which a set of reference image/shape masks is used to find multiple objects. We design a novel CRF framework that jointly models object appearance, shape deformation, and object occlusion. To tackle the challenging MAP inference problem, we derive an alternating procedure that interleaves object segmentation and shape/appearance adaptation. We evaluate our method on two datasets with instance labels and show promising results.

Original language	English
Title of host publication	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publisher	IEEE Computer Society
Pages	296-303
Number of pages	8
ISBN (Electronic)	9781479951178, 9781479951178
DOIs	https://doi.org/10.1109/CVPR.2014.45
Publication status	Published - 24 Sept 2014
Event	27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 - Columbus, United States Duration: 23 Jun 2014 → 28 Jun 2014

Publication series

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

Conference

Conference	27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
Country/Territory	United States
City	Columbus
Period	23/06/14 → 28/06/14

Access to Document

10.1109/CVPR.2014.45

Cite this

He, X., & Gould, S. (2014). An exemplar-based CRF for multi-instance object segmentation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 296-303). Article 6909439 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). IEEE Computer Society. https://doi.org/10.1109/CVPR.2014.45

@inproceedings{433edfed410545c293569802877ebb9c,

title = "An exemplar-based CRF for multi-instance object segmentation",

abstract = "We address the problem of joint detection and segmentation of multiple object instances in an image, a key step towards scene understanding. Inspired by data-driven methods, we propose an exemplar-based approach to the task of instance segmentation, in which a set of reference image/shape masks is used to find multiple objects. We design a novel CRF framework that jointly models object appearance, shape deformation, and object occlusion. To tackle the challenging MAP inference problem, we derive an alternating procedure that interleaves object segmentation and shape/appearance adaptation. We evaluate our method on two datasets with instance labels and show promising results.",

author = "Xuming He and Stephen Gould",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 ; Conference date: 23-06-2014 Through 28-06-2014",

year = "2014",

month = sep,

day = "24",

doi = "10.1109/CVPR.2014.45",

language = "English",

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

publisher = "IEEE Computer Society",

pages = "296--303",

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

address = "United States",

}

He, X & Gould, S 2014, An exemplar-based CRF for multi-instance object segmentation. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 6909439, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, pp. 296-303, 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, United States, 23/06/14. https://doi.org/10.1109/CVPR.2014.45

An exemplar-based CRF for multi-instance object segmentation. / He, Xuming; Gould, Stephen.
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2014. p. 296-303 6909439 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

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

TY - GEN

T1 - An exemplar-based CRF for multi-instance object segmentation

AU - He, Xuming

AU - Gould, Stephen

PY - 2014/9/24

Y1 - 2014/9/24

N2 - We address the problem of joint detection and segmentation of multiple object instances in an image, a key step towards scene understanding. Inspired by data-driven methods, we propose an exemplar-based approach to the task of instance segmentation, in which a set of reference image/shape masks is used to find multiple objects. We design a novel CRF framework that jointly models object appearance, shape deformation, and object occlusion. To tackle the challenging MAP inference problem, we derive an alternating procedure that interleaves object segmentation and shape/appearance adaptation. We evaluate our method on two datasets with instance labels and show promising results.

AB - We address the problem of joint detection and segmentation of multiple object instances in an image, a key step towards scene understanding. Inspired by data-driven methods, we propose an exemplar-based approach to the task of instance segmentation, in which a set of reference image/shape masks is used to find multiple objects. We design a novel CRF framework that jointly models object appearance, shape deformation, and object occlusion. To tackle the challenging MAP inference problem, we derive an alternating procedure that interleaves object segmentation and shape/appearance adaptation. We evaluate our method on two datasets with instance labels and show promising results.

UR - http://www.scopus.com/inward/record.url?scp=84911430631&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2014.45

DO - 10.1109/CVPR.2014.45

M3 - Conference contribution

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

SP - 296

EP - 303

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

PB - IEEE Computer Society

T2 - 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014

Y2 - 23 June 2014 through 28 June 2014

ER -

An exemplar-based CRF for multi-instance object segmentation

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this