Abstract
In this paper we study the role of context in existing state-of-the-art detection and segmentation approaches. Towards this goal, we label every pixel of PASCAL VOC 2010 detection challenge with a semantic category. We believe this data will provide plenty of challenges to the community, as it contains 520 additional classes for semantic segmentation and object detection. Our analysis shows that nearest neighbor based approaches perform poorly on semantic segmentation of contextual classes, showing the variability of PASCAL imagery. Furthermore, improvements of exist ing contextual models for detection is rather modest. In order to push forward the performance in this difficult scenario, we propose a novel deformable part-based model, which exploits both local context around each candidate detection as well as global context at the level of the scene. We show that this contextual reasoning significantly helps in detecting objects at all scales.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
| Publisher | IEEE Computer Society |
| Pages | 891-898 |
| Number of pages | 8 |
| ISBN (Print) | 9781479951178, 9781479951178 |
| DOIs | |
| Publication status | Published - 2014 Jan 1 |
| Event | 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 - Columbus, United States Duration: 2014 Jun 23 → 2014 Jun 28 |
Other
| Other | 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 |
|---|---|
| Country | United States |
| City | Columbus |
| Period | 14/6/23 → 14/6/28 |
Fingerprint
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition
Cite this
The role of context for object detection and semantic segmentation in the wild. / Mottaghi, Roozbeh; Chen, Xianjie; Liu, Xiaobai; Cho, Nam Gyu; Lee, Seong Whan; Fidler, Sanja; Urtasun, Raquel; Yuille, Alan.
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2014. p. 891-898 6909514.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - The role of context for object detection and semantic segmentation in the wild
AU - Mottaghi, Roozbeh
AU - Chen, Xianjie
AU - Liu, Xiaobai
AU - Cho, Nam Gyu
AU - Lee, Seong Whan
AU - Fidler, Sanja
AU - Urtasun, Raquel
AU - Yuille, Alan
PY - 2014/1/1
Y1 - 2014/1/1
N2 - In this paper we study the role of context in existing state-of-the-art detection and segmentation approaches. Towards this goal, we label every pixel of PASCAL VOC 2010 detection challenge with a semantic category. We believe this data will provide plenty of challenges to the community, as it contains 520 additional classes for semantic segmentation and object detection. Our analysis shows that nearest neighbor based approaches perform poorly on semantic segmentation of contextual classes, showing the variability of PASCAL imagery. Furthermore, improvements of exist ing contextual models for detection is rather modest. In order to push forward the performance in this difficult scenario, we propose a novel deformable part-based model, which exploits both local context around each candidate detection as well as global context at the level of the scene. We show that this contextual reasoning significantly helps in detecting objects at all scales.
AB - In this paper we study the role of context in existing state-of-the-art detection and segmentation approaches. Towards this goal, we label every pixel of PASCAL VOC 2010 detection challenge with a semantic category. We believe this data will provide plenty of challenges to the community, as it contains 520 additional classes for semantic segmentation and object detection. Our analysis shows that nearest neighbor based approaches perform poorly on semantic segmentation of contextual classes, showing the variability of PASCAL imagery. Furthermore, improvements of exist ing contextual models for detection is rather modest. In order to push forward the performance in this difficult scenario, we propose a novel deformable part-based model, which exploits both local context around each candidate detection as well as global context at the level of the scene. We show that this contextual reasoning significantly helps in detecting objects at all scales.
UR - http://www.scopus.com/inward/record.url?scp=84911444024&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84911444024&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2014.119
DO - 10.1109/CVPR.2014.119
M3 - Conference contribution
AN - SCOPUS:84911444024
SN - 9781479951178
SN - 9781479951178
SP - 891
EP - 898
BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PB - IEEE Computer Society
ER -