Interactive image segmentation via backpropagating refinement scheme

Won Dong Jang; Chang Su Kim

doi:10.1109/CVPR.2019.00544

Interactive image segmentation via backpropagating refinement scheme

Won Dong Jang, Chang Su Kim

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

111 Citations (Scopus)

Abstract

An interactive image segmentation algorithm, which accepts user-annotations about a target object and the background, is proposed in this work. We convert user-annotations into interaction maps by measuring distances of each pixel to the annotated locations. Then, we perform the forward pass in a convolutional neural network, which outputs an initial segmentation map. However, the user-annotated locations can be mislabeled in the initial result. Therefore, we develop the backpropagating refinement scheme (BRS), which corrects the mislabeled pixels. Experimental results demonstrate that the proposed algorithm outperforms the conventional algorithms on four challenging datasets. Furthermore, we demonstrate the generality and applicability of BRS in other computer vision tasks, by transforming existing convolutional neural networks into user-interactive ones.

Original language	English
Title of host publication	Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Publisher	IEEE Computer Society
Pages	5292-5301
Number of pages	10
ISBN (Electronic)	9781728132938
DOIs	https://doi.org/10.1109/CVPR.2019.00544
Publication status	Published - 2019 Jun
Event	32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 - Long Beach, United States Duration: 2019 Jun 16 → 2019 Jun 20

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2019-June
ISSN (Print)	1063-6919

Conference

Conference	32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Country/Territory	United States
City	Long Beach
Period	19/6/16 → 19/6/20

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Grouping and Shape
Segmentation

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2019.00544

Cite this

Jang, W. D., & Kim, C. S. (2019). Interactive image segmentation via backpropagating refinement scheme. In Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 (pp. 5292-5301). Article 8953578 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2019-June). IEEE Computer Society. https://doi.org/10.1109/CVPR.2019.00544

Interactive image segmentation via backpropagating refinement scheme. / Jang, Won Dong; Kim, Chang Su.
Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019. IEEE Computer Society, 2019. p. 5292-5301 8953578 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2019-June).

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

Jang, WD & Kim, CS 2019, Interactive image segmentation via backpropagating refinement scheme. in Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019., 8953578, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2019-June, IEEE Computer Society, pp. 5292-5301, 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, United States, 19/6/16. https://doi.org/10.1109/CVPR.2019.00544

@inproceedings{855eb6ce55464963b787fcee67d9210a,

title = "Interactive image segmentation via backpropagating refinement scheme",

abstract = "An interactive image segmentation algorithm, which accepts user-annotations about a target object and the background, is proposed in this work. We convert user-annotations into interaction maps by measuring distances of each pixel to the annotated locations. Then, we perform the forward pass in a convolutional neural network, which outputs an initial segmentation map. However, the user-annotated locations can be mislabeled in the initial result. Therefore, we develop the backpropagating refinement scheme (BRS), which corrects the mislabeled pixels. Experimental results demonstrate that the proposed algorithm outperforms the conventional algorithms on four challenging datasets. Furthermore, we demonstrate the generality and applicability of BRS in other computer vision tasks, by transforming existing convolutional neural networks into user-interactive ones.",

keywords = "Grouping and Shape, Segmentation",

author = "Jang, {Won Dong} and Kim, {Chang Su}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 ; Conference date: 16-06-2019 Through 20-06-2019",

year = "2019",

month = jun,

doi = "10.1109/CVPR.2019.00544",

language = "English",

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

publisher = "IEEE Computer Society",

pages = "5292--5301",

booktitle = "Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019",

}

TY - GEN

T1 - Interactive image segmentation via backpropagating refinement scheme

AU - Jang, Won Dong

AU - Kim, Chang Su

PY - 2019/6

Y1 - 2019/6

N2 - An interactive image segmentation algorithm, which accepts user-annotations about a target object and the background, is proposed in this work. We convert user-annotations into interaction maps by measuring distances of each pixel to the annotated locations. Then, we perform the forward pass in a convolutional neural network, which outputs an initial segmentation map. However, the user-annotated locations can be mislabeled in the initial result. Therefore, we develop the backpropagating refinement scheme (BRS), which corrects the mislabeled pixels. Experimental results demonstrate that the proposed algorithm outperforms the conventional algorithms on four challenging datasets. Furthermore, we demonstrate the generality and applicability of BRS in other computer vision tasks, by transforming existing convolutional neural networks into user-interactive ones.

AB - An interactive image segmentation algorithm, which accepts user-annotations about a target object and the background, is proposed in this work. We convert user-annotations into interaction maps by measuring distances of each pixel to the annotated locations. Then, we perform the forward pass in a convolutional neural network, which outputs an initial segmentation map. However, the user-annotated locations can be mislabeled in the initial result. Therefore, we develop the backpropagating refinement scheme (BRS), which corrects the mislabeled pixels. Experimental results demonstrate that the proposed algorithm outperforms the conventional algorithms on four challenging datasets. Furthermore, we demonstrate the generality and applicability of BRS in other computer vision tasks, by transforming existing convolutional neural networks into user-interactive ones.

KW - Grouping and Shape

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85076167309&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2019.00544

DO - 10.1109/CVPR.2019.00544

M3 - Conference contribution

AN - SCOPUS:85076167309

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

SP - 5292

EP - 5301

BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019

PB - IEEE Computer Society

T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019

Y2 - 16 June 2019 through 20 June 2019

ER -

Interactive image segmentation via backpropagating refinement scheme

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this