Adaptive region pooling for object detection

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 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 languageEnglish
Title of host publicationIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
PublisherIEEE Computer Society
Pages731-739
Number of pages9
ISBN (Electronic)9781467369640
DOIs
Publication statusPublished - 2015 Oct 14
EventIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States
Duration: 2015 Jun 72015 Jun 12

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume07-12-June-2015
ISSN (Print)1063-6919

Other

OtherIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
CountryUnited States
CityBoston
Period15/6/715/6/12

Fingerprint

Volatile organic compounds
Rigidity
Object detection

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

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
Tsai, Yi Hsuan ; Hamsici, Onur C. ; Yang, Ming Hsuan. / Adaptive region pooling for object detection. IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. pp. 731-739 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@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}",
year = "2015",
month = "10",
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 proceedingConference 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

ER -

Tsai YH, Hamsici OC, Yang MH. Adaptive region pooling for object detection. In 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). https://doi.org/10.1109/CVPR.2015.7298673