Objects as Context for Detecting Their Semantic Parts

Abel Gonzalez-Garcia; Davide Modolo; Vittorio Ferrari

doi:10.1109/CVPR.2018.00722

Objects as Context for Detecting Their Semantic Parts

Abel Gonzalez-Garcia, Davide Modolo, Vittorio Ferrari

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

Abstract

We present a semantic part detection approach that effectively leverages object information. We use the object appearance and its class as indicators of what parts to expect. We also model the expected relative location of parts inside the objects based on their appearance. We achieve this with a new network module, called OffsetNet, that efficiently predicts a variable number of part locations within a given object. Our model incorporates all these cues to detect parts in the context of their objects. This leads to considerably higher performance for the challenging task of part detection compared to using part appearance alone
(+5 mAP on the PASCAL-Part dataset). We also compare to other part detection methods on both PASCAL-Part and CUB200-2011 datasets.

Original language	English
Title of host publication	The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Pages	6907-6916
Number of pages	10
DOIs	https://doi.org/10.1109/CVPR.2018.00722
Publication status	Published - 17 Dec 2018
Event	Computer Vision and Pattern Recognition 2018 - Salt Lake City, United States Duration: 18 Jun 2018 → 22 Jun 2018 http://cvpr2018.thecvf.com/ http://cvpr2018.thecvf.com/ http://cvpr2018.thecvf.com/

Publication series

Name
Publisher	IEEE
ISSN (Print)	1063-6919
ISSN (Electronic)	2575-7075

Conference

Conference	Computer Vision and Pattern Recognition 2018
Abbreviated title	CVPR 2018
Country/Territory	United States
City	Salt Lake City
Period	18/06/18 → 22/06/18
Internet address	http://cvpr2018.thecvf.com/ http://cvpr2018.thecvf.com/ http://cvpr2018.thecvf.com/

Access to Document

10.1109/CVPR.2018.00722

gonzalez18cvprAccepted author manuscript, 8.88 MB

VISCUL - Visual culture for image understanding
Ferrari, V. (Principal Investigator)
EU government bodies
1/01/13 → 31/12/17
Project: Research

Cite this

@inproceedings{b08da4b3a3ce44d8abaae83b675f9dbc,

title = "Objects as Context for Detecting Their Semantic Parts",

abstract = "We present a semantic part detection approach that effectively leverages object information. We use the object appearance and its class as indicators of what parts to expect. We also model the expected relative location of parts inside the objects based on their appearance. We achieve this with a new network module, called OffsetNet, that efficiently predicts a variable number of part locations within a given object. Our model incorporates all these cues to detect parts in the context of their objects. This leads to considerably higher performance for the challenging task of part detection compared to using part appearance alone(+5 mAP on the PASCAL-Part dataset). We also compare to other part detection methods on both PASCAL-Part and CUB200-2011 datasets.",

author = "Abel Gonzalez-Garcia and Davide Modolo and Vittorio Ferrari",

year = "2018",

month = dec,

day = "17",

doi = "10.1109/CVPR.2018.00722",

language = "English",

publisher = "IEEE",

pages = "6907--6916",

booktitle = "The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)",

note = "Computer Vision and Pattern Recognition 2018, CVPR 2018 ; Conference date: 18-06-2018 Through 22-06-2018",

url = "http://cvpr2018.thecvf.com/, http://cvpr2018.thecvf.com/, http://cvpr2018.thecvf.com/",

}

TY - GEN

T1 - Objects as Context for Detecting Their Semantic Parts

AU - Gonzalez-Garcia, Abel

AU - Modolo, Davide

AU - Ferrari, Vittorio

PY - 2018/12/17

Y1 - 2018/12/17

N2 - We present a semantic part detection approach that effectively leverages object information. We use the object appearance and its class as indicators of what parts to expect. We also model the expected relative location of parts inside the objects based on their appearance. We achieve this with a new network module, called OffsetNet, that efficiently predicts a variable number of part locations within a given object. Our model incorporates all these cues to detect parts in the context of their objects. This leads to considerably higher performance for the challenging task of part detection compared to using part appearance alone(+5 mAP on the PASCAL-Part dataset). We also compare to other part detection methods on both PASCAL-Part and CUB200-2011 datasets.

AB - We present a semantic part detection approach that effectively leverages object information. We use the object appearance and its class as indicators of what parts to expect. We also model the expected relative location of parts inside the objects based on their appearance. We achieve this with a new network module, called OffsetNet, that efficiently predicts a variable number of part locations within a given object. Our model incorporates all these cues to detect parts in the context of their objects. This leads to considerably higher performance for the challenging task of part detection compared to using part appearance alone(+5 mAP on the PASCAL-Part dataset). We also compare to other part detection methods on both PASCAL-Part and CUB200-2011 datasets.

U2 - 10.1109/CVPR.2018.00722

DO - 10.1109/CVPR.2018.00722

M3 - Conference contribution

SP - 6907

EP - 6916

BT - The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

T2 - Computer Vision and Pattern Recognition 2018

Y2 - 18 June 2018 through 22 June 2018

ER -

Objects as Context for Detecting Their Semantic Parts

Abstract

Publication series

Conference

Access to Document

Fingerprint

Projects

VISCUL - Visual culture for image understanding

Cite this