Conference item icon

Conference item

A projected gradient descent method for CRF inference allowing end-to-end training of arbitrary pairwise potentials

Abstract:

Are we using the right potential functions in the Conditional Random Field models that are popular in the Vision community? Semantic segmentation and other pixel-level labelling tasks have made significant progress recently due to the deep learning paradigm. However, most state-of-the-art structured prediction methods also include a random field model with a hand-crafted Gaussian potential to model spatial priors, label consistencies and feature-based image conditioning.


In th...

Expand abstract
Publication status:
Published
Peer review status:
Reviewed (other)

Actions


Access Document


Files:
Publisher copy:
10.1007/978-3-319-78199-0_37

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
Swedish Foundation for Strategic Research More from this funder
Swedish Research Council More from this funder
More from this funder
Grant:
ERC-2012-AdG 321162-HELIOS
Publisher:
Springer Publisher's website
Journal:
Energy Minimization Methods in Computer Vision and Pattern Recognition Journal website
Host title:
11th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR 2017)
Publication date:
2018-03-22
Acceptance date:
2017-09-25
DOI:
Source identifiers:
828170
Keywords:
Pubs id:
pubs:828170
UUID:
uuid:5cbdbaa8-b1e8-4d2c-99dd-616ec359cf09
Local pid:
pubs:828170
Deposit date:
2018-03-07

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP