Mining discriminative triplets of patches for fine-grained classification

Yaming Wang; Jonghyun Choi; Vlad I. Morariu; Larr S. Davis

doi:10.1109/CVPR.2016.131

Mining discriminative triplets of patches for fine-grained classification

Yaming Wang, Jonghyun Choi, Vlad I. Morariu, Larr S. Davis

Department of Artificial Intelligence

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

96 Citations (Scopus)

Abstract

Fine-grained classification involves distinguishing between similar sub-categories based on subtle differences in highly localized regions, therefore, accurate localization of discriminative regions remains a major challenge. We describe a patch-based framework to address this problem. We introduce triplets of patches with geometric constraints to improve the accuracy of patch localization, and automatically mine discriminative geometrically-constrained triplets for classification. The resulting approach only requires object bounding boxes. Its effectiveness is demonstrated using four publicly available fine-grained datasets, on which it outperforms or achieves comparable performance to the state-of-the-art in classification.

Original language	English
Title of host publication	Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Publisher	IEEE Computer Society
Pages	1163-1172
Number of pages	10
ISBN (Electronic)	9781467388504
DOIs	https://doi.org/10.1109/CVPR.2016.131
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:
This work was partially supported by ONR MURI Grant N000141010934.

Publisher Copyright:
© 2016 IEEE.

All Science Journal Classification (ASJC) codes

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2016.131

Cite this

Wang, Y., Choi, J., Morariu, V. I., & Davis, L. S. (2016). Mining discriminative triplets of patches for fine-grained classification. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 (pp. 1163-1172). [7780500] (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.2016.131

@inproceedings{66ee5bc14ffa4ceca9ac7d6e1dc371b2,

title = "Mining discriminative triplets of patches for fine-grained classification",

abstract = "Fine-grained classification involves distinguishing between similar sub-categories based on subtle differences in highly localized regions, therefore, accurate localization of discriminative regions remains a major challenge. We describe a patch-based framework to address this problem. We introduce triplets of patches with geometric constraints to improve the accuracy of patch localization, and automatically mine discriminative geometrically-constrained triplets for classification. The resulting approach only requires object bounding boxes. Its effectiveness is demonstrated using four publicly available fine-grained datasets, on which it outperforms or achieves comparable performance to the state-of-the-art in classification.",

author = "Yaming Wang and Jonghyun Choi and Morariu, {Vlad I.} and Davis, {Larr S.}",

note = "Funding Information: This work was partially supported by ONR MURI Grant N000141010934. 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.2016.131",

language = "English",

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

publisher = "IEEE Computer Society",

pages = "1163--1172",

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

address = "United States",

}

Wang, Y, Choi, J, Morariu, VI & Davis, LS 2016, Mining discriminative triplets of patches for fine-grained classification. in Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016., 7780500, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, IEEE Computer Society, pp. 1163-1172, 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, United States, 16/6/26. https://doi.org/10.1109/CVPR.2016.131

Mining discriminative triplets of patches for fine-grained classification. / Wang, Yaming; Choi, Jonghyun; Morariu, Vlad I. et al.

Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. p. 1163-1172 7780500 (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 - Mining discriminative triplets of patches for fine-grained classification

AU - Wang, Yaming

AU - Choi, Jonghyun

AU - Morariu, Vlad I.

AU - Davis, Larr S.

PY - 2016/12/9

Y1 - 2016/12/9

N2 - Fine-grained classification involves distinguishing between similar sub-categories based on subtle differences in highly localized regions, therefore, accurate localization of discriminative regions remains a major challenge. We describe a patch-based framework to address this problem. We introduce triplets of patches with geometric constraints to improve the accuracy of patch localization, and automatically mine discriminative geometrically-constrained triplets for classification. The resulting approach only requires object bounding boxes. Its effectiveness is demonstrated using four publicly available fine-grained datasets, on which it outperforms or achieves comparable performance to the state-of-the-art in classification.

AB - Fine-grained classification involves distinguishing between similar sub-categories based on subtle differences in highly localized regions, therefore, accurate localization of discriminative regions remains a major challenge. We describe a patch-based framework to address this problem. We introduce triplets of patches with geometric constraints to improve the accuracy of patch localization, and automatically mine discriminative geometrically-constrained triplets for classification. The resulting approach only requires object bounding boxes. Its effectiveness is demonstrated using four publicly available fine-grained datasets, on which it outperforms or achieves comparable performance to the state-of-the-art in classification.

UR - http://www.scopus.com/inward/record.url?scp=84986331520&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986331520&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2016.131

DO - 10.1109/CVPR.2016.131

M3 - Conference contribution

AN - SCOPUS:84986331520

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

SP - 1163

EP - 1172

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 -

Wang Y, Choi J, Morariu VI, Davis LS. Mining discriminative triplets of patches for fine-grained classification. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society. 2016. p. 1163-1172. 7780500. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). doi: 10.1109/CVPR.2016.131

Mining discriminative triplets of patches for fine-grained classification

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this