Adaptive region pooling for object detection

Yi Hsuan Tsai; Onur C. Hamsici; Ming Hsuan Yang

doi:10.1109/CVPR.2015.7298673

Adaptive region pooling for object detection

Yi Hsuan Tsai, Onur C. Hamsici, Ming Hsuan Yang

Department of Computer Science

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

14 Citations (Scopus)

Abstract

Learning models for object detection is a challenging problem due to the large intra-class variability of objects in appearance, viewpoints, and rigidity. We address this variability by a novel feature pooling method that is adaptive to segmented regions. The proposed detection algorithm automatically discovers a diverse set of exemplars and their distinctive parts which are used to encode the region structure by the proposed feature pooling method. Based on each exemplar and its parts, a regression model is learned with samples selected by a coarse region matching scheme. The proposed algorithm performs favorably on the PASCAL VOC 2007 dataset against existing algorithms. We demonstrate the benefits of our feature pooling method when compared to conventional spatial pyramid pooling features. We also show that object information can be transferred through exemplars for detected objects.

Original language	English
Title of host publication	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Publisher	IEEE Computer Society
Pages	731-739
Number of pages	9
ISBN (Electronic)	9781467369640
DOIs	https://doi.org/10.1109/CVPR.2015.7298673
Publication status	Published - 2015 Oct 14
Event	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States Duration: 2015 Jun 7 → 2015 Jun 12

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	07-12-June-2015
ISSN (Print)	1063-6919

Other

Other	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Country	United States
City	Boston
Period	15/6/7 → 15/6/12

All Science Journal Classification (ASJC) codes

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2015.7298673

Fingerprint Dive into the research topics of 'Adaptive region pooling for object detection'. Together they form a unique fingerprint.

Cite this

Tsai, Y. H., Hamsici, O. C., & Yang, M. H. (2015). Adaptive region pooling for object detection. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 (pp. 731-739). [7298673] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015). IEEE Computer Society. https://doi.org/10.1109/CVPR.2015.7298673

@inproceedings{902ef07ad4284e68ab4a9393482a678f,

title = "Adaptive region pooling for object detection",

abstract = "Learning models for object detection is a challenging problem due to the large intra-class variability of objects in appearance, viewpoints, and rigidity. We address this variability by a novel feature pooling method that is adaptive to segmented regions. The proposed detection algorithm automatically discovers a diverse set of exemplars and their distinctive parts which are used to encode the region structure by the proposed feature pooling method. Based on each exemplar and its parts, a regression model is learned with samples selected by a coarse region matching scheme. The proposed algorithm performs favorably on the PASCAL VOC 2007 dataset against existing algorithms. We demonstrate the benefits of our feature pooling method when compared to conventional spatial pyramid pooling features. We also show that object information can be transferred through exemplars for detected objects.",

author = "Tsai, {Yi Hsuan} and Hamsici, {Onur C.} and Yang, {Ming Hsuan}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE. Copyright: Copyright 2017 Elsevier B.V., All rights reserved.; IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 ; Conference date: 07-06-2015 Through 12-06-2015",

year = "2015",

month = oct,

day = "14",

doi = "10.1109/CVPR.2015.7298673",

language = "English",

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

publisher = "IEEE Computer Society",

pages = "731--739",

booktitle = "IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015",

address = "United States",

}

Tsai, YH, Hamsici, OC & Yang, MH 2015, Adaptive region pooling for object detection. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015., 7298673, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07-12-June-2015, IEEE Computer Society, pp. 731-739, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 15/6/7. https://doi.org/10.1109/CVPR.2015.7298673

Adaptive region pooling for object detection. / Tsai, Yi Hsuan; Hamsici, Onur C.; Yang, Ming Hsuan.

IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. p. 731-739 7298673 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015).

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

TY - GEN

T1 - Adaptive region pooling for object detection

AU - Tsai, Yi Hsuan

AU - Hamsici, Onur C.

AU - Yang, Ming Hsuan

PY - 2015/10/14

Y1 - 2015/10/14

N2 - Learning models for object detection is a challenging problem due to the large intra-class variability of objects in appearance, viewpoints, and rigidity. We address this variability by a novel feature pooling method that is adaptive to segmented regions. The proposed detection algorithm automatically discovers a diverse set of exemplars and their distinctive parts which are used to encode the region structure by the proposed feature pooling method. Based on each exemplar and its parts, a regression model is learned with samples selected by a coarse region matching scheme. The proposed algorithm performs favorably on the PASCAL VOC 2007 dataset against existing algorithms. We demonstrate the benefits of our feature pooling method when compared to conventional spatial pyramid pooling features. We also show that object information can be transferred through exemplars for detected objects.

AB - Learning models for object detection is a challenging problem due to the large intra-class variability of objects in appearance, viewpoints, and rigidity. We address this variability by a novel feature pooling method that is adaptive to segmented regions. The proposed detection algorithm automatically discovers a diverse set of exemplars and their distinctive parts which are used to encode the region structure by the proposed feature pooling method. Based on each exemplar and its parts, a regression model is learned with samples selected by a coarse region matching scheme. The proposed algorithm performs favorably on the PASCAL VOC 2007 dataset against existing algorithms. We demonstrate the benefits of our feature pooling method when compared to conventional spatial pyramid pooling features. We also show that object information can be transferred through exemplars for detected objects.

UR - http://www.scopus.com/inward/record.url?scp=84959208354&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959208354&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2015.7298673

DO - 10.1109/CVPR.2015.7298673

M3 - Conference contribution

AN - SCOPUS:84959208354

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

SP - 731

EP - 739

BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

PB - IEEE Computer Society

T2 - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

Y2 - 7 June 2015 through 12 June 2015

ER -