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 | |
| 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 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Computer Vision and Pattern Recognition
Cite this
}
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
ER -