Object contour detection with a fully convolutional encoder-decoder network

Jimei Yang; Brian Price; Scott Cohen; Honglak Lee; Ming Hsuan Yang

doi:10.1109/CVPR.2016.28

Object contour detection with a fully convolutional encoder-decoder network

Jimei Yang, Brian Price, Scott Cohen, Honglak Lee, Ming Hsuan Yang

College of Computing

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

267 Citations (Scopus)

Abstract

We develop a deep learning algorithm for contour detection with a fully convolutional encoder-decoder network. Different from previous low-level edge detection, our algorithm focuses on detecting higher-level object contours. Our network is trained end-to-end on PASCAL VOC with refined ground truth from inaccurate polygon annotations, yielding much higher precision in object contour detection than previous methods. We find that the learned model generalizes well to unseen object classes from the same supercategories on MS COCO and can match state-of-the-art edge detection on BSDS500 with fine-tuning. By combining with the multiscale combinatorial grouping algorithm, our method can generate high-quality segmented object proposals, which significantly advance the state-of-the-art on PASCAL VOC (improving average recall from 0.62 to 0.67) with a relatively small amount of candidates (~1660 per image).

Original language	English
Title of host publication	Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Publisher	IEEE Computer Society
Pages	193-202
Number of pages	10
ISBN (Electronic)	9781467388504
DOIs	https://doi.org/10.1109/CVPR.2016.28
Publication status	Published - 2016 Dec 9
Event	29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States Duration: 2016 Jun 26 → 2016 Jul 1

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2016-December
ISSN (Print)	1063-6919

Conference

Conference	29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Country/Territory	United States
City	Las Vegas
Period	16/6/26 → 16/7/1

Bibliographical note

Funding Information:
J. Yang and M.-H. Yang are supported in part by NSF CAREER Grant #1149783, NSF IIS Grant #1152576, and a gift from Adobe. H. Lee is supported in part by NSF CAREER Grant IIS-1453651.

Publisher Copyright:
© 2016 IEEE.

All Science Journal Classification (ASJC) codes

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2016.28

Cite this

Yang, J., Price, B., Cohen, S., Lee, H., & Yang, M. H. (2016). Object contour detection with a fully convolutional encoder-decoder network. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 (pp. 193-202). [7780397] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December). IEEE Computer Society. https://doi.org/10.1109/CVPR.2016.28

@inproceedings{bcf6061826f64ed3b19a547d00276532,

title = "Object contour detection with a fully convolutional encoder-decoder network",

abstract = "We develop a deep learning algorithm for contour detection with a fully convolutional encoder-decoder network. Different from previous low-level edge detection, our algorithm focuses on detecting higher-level object contours. Our network is trained end-to-end on PASCAL VOC with refined ground truth from inaccurate polygon annotations, yielding much higher precision in object contour detection than previous methods. We find that the learned model generalizes well to unseen object classes from the same supercategories on MS COCO and can match state-of-the-art edge detection on BSDS500 with fine-tuning. By combining with the multiscale combinatorial grouping algorithm, our method can generate high-quality segmented object proposals, which significantly advance the state-of-the-art on PASCAL VOC (improving average recall from 0.62 to 0.67) with a relatively small amount of candidates (~1660 per image).",

author = "Jimei Yang and Brian Price and Scott Cohen and Honglak Lee and Yang, {Ming Hsuan}",

note = "Funding Information: J. Yang and M.-H. Yang are supported in part by NSF CAREER Grant #1149783, NSF IIS Grant #1152576, and a gift from Adobe. H. Lee is supported in part by NSF CAREER Grant IIS-1453651. Publisher Copyright: {\textcopyright} 2016 IEEE.; 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 ; Conference date: 26-06-2016 Through 01-07-2016",

year = "2016",

month = dec,

day = "9",

doi = "10.1109/CVPR.2016.28",

language = "English",

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

publisher = "IEEE Computer Society",

pages = "193--202",

booktitle = "Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016",

address = "United States",

}

Yang, J, Price, B, Cohen, S, Lee, H & Yang, MH 2016, Object contour detection with a fully convolutional encoder-decoder network. in Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016., 7780397, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, IEEE Computer Society, pp. 193-202, 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, United States, 16/6/26. https://doi.org/10.1109/CVPR.2016.28

Object contour detection with a fully convolutional encoder-decoder network. / Yang, Jimei; Price, Brian; Cohen, Scott et al.

Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. p. 193-202 7780397 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December).

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

TY - GEN

T1 - Object contour detection with a fully convolutional encoder-decoder network

AU - Yang, Jimei

AU - Price, Brian

AU - Cohen, Scott

AU - Lee, Honglak

AU - Yang, Ming Hsuan

N1 - Funding Information: J. Yang and M.-H. Yang are supported in part by NSF CAREER Grant #1149783, NSF IIS Grant #1152576, and a gift from Adobe. H. Lee is supported in part by NSF CAREER Grant IIS-1453651. Publisher Copyright: © 2016 IEEE.

PY - 2016/12/9

Y1 - 2016/12/9

N2 - We develop a deep learning algorithm for contour detection with a fully convolutional encoder-decoder network. Different from previous low-level edge detection, our algorithm focuses on detecting higher-level object contours. Our network is trained end-to-end on PASCAL VOC with refined ground truth from inaccurate polygon annotations, yielding much higher precision in object contour detection than previous methods. We find that the learned model generalizes well to unseen object classes from the same supercategories on MS COCO and can match state-of-the-art edge detection on BSDS500 with fine-tuning. By combining with the multiscale combinatorial grouping algorithm, our method can generate high-quality segmented object proposals, which significantly advance the state-of-the-art on PASCAL VOC (improving average recall from 0.62 to 0.67) with a relatively small amount of candidates (~1660 per image).

AB - We develop a deep learning algorithm for contour detection with a fully convolutional encoder-decoder network. Different from previous low-level edge detection, our algorithm focuses on detecting higher-level object contours. Our network is trained end-to-end on PASCAL VOC with refined ground truth from inaccurate polygon annotations, yielding much higher precision in object contour detection than previous methods. We find that the learned model generalizes well to unseen object classes from the same supercategories on MS COCO and can match state-of-the-art edge detection on BSDS500 with fine-tuning. By combining with the multiscale combinatorial grouping algorithm, our method can generate high-quality segmented object proposals, which significantly advance the state-of-the-art on PASCAL VOC (improving average recall from 0.62 to 0.67) with a relatively small amount of candidates (~1660 per image).

UR - http://www.scopus.com/inward/record.url?scp=84986265719&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986265719&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2016.28

DO - 10.1109/CVPR.2016.28

M3 - Conference contribution

AN - SCOPUS:84986265719

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

SP - 193

EP - 202

BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

PB - IEEE Computer Society

T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

Y2 - 26 June 2016 through 1 July 2016

ER -

Yang J, Price B, Cohen S, Lee H, Yang MH. Object contour detection with a fully convolutional encoder-decoder network. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society. 2016. p. 193-202. 7780397. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). doi: 10.1109/CVPR.2016.28

Object contour detection with a fully convolutional encoder-decoder network

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this