The role of context for object detection and semantic segmentation in the wild

Roozbeh Mottaghi, Xianjie Chen, Xiaobai Liu, Nam Gyu Cho, Seong Whan Lee, Sanja Fidler, Raquel Urtasun, Alan Yuille

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

273 Citations (Scopus)

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 languageEnglish
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE Computer Society
Pages891-898
Number of pages8
ISBN (Print)9781479951178, 9781479951178
DOIs
Publication statusPublished - 2014 Jan 1
Event27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 - Columbus, United States
Duration: 2014 Jun 232014 Jun 28

Other

Other27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014
CountryUnited States
CityColumbus
Period14/6/2314/6/28

Fingerprint

Semantics
Volatile organic compounds
Labels
Pixels
Object detection

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Mottaghi, R., Chen, X., Liu, X., Cho, N. G., Lee, S. W., Fidler, S., ... Yuille, A. (2014). The role of context for object detection and semantic segmentation in the wild. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 891-898). [6909514] IEEE Computer Society. https://doi.org/10.1109/CVPR.2014.119

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 proceedingConference contribution

Mottaghi, R, Chen, X, Liu, X, Cho, NG, Lee, SW, Fidler, S, Urtasun, R & Yuille, A 2014, The role of context for object detection and semantic segmentation in the wild. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 6909514, IEEE Computer Society, pp. 891-898, 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, United States, 14/6/23. https://doi.org/10.1109/CVPR.2014.119
Mottaghi R, Chen X, Liu X, Cho NG, Lee SW, Fidler S et al. The role of context for object detection and semantic segmentation in the wild. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society. 2014. p. 891-898. 6909514 https://doi.org/10.1109/CVPR.2014.119
Mottaghi, Roozbeh ; Chen, Xianjie ; Liu, Xiaobai ; Cho, Nam Gyu ; Lee, Seong Whan ; Fidler, Sanja ; Urtasun, Raquel ; Yuille, Alan. / The role of context for object detection and semantic segmentation in the wild. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2014. pp. 891-898
@inproceedings{3a226a67598044949605c22149f55a45,
title = "The role of context for object detection and semantic segmentation in the wild",
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.",
author = "Roozbeh Mottaghi and Xianjie Chen and Xiaobai Liu and Cho, {Nam Gyu} and Lee, {Seong Whan} and Sanja Fidler and Raquel Urtasun and Alan Yuille",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/CVPR.2014.119",
language = "English",
isbn = "9781479951178",
pages = "891--898",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",

}

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 -