Conference item icon

Conference item

Efficient linear programming for dense CRFs

Abstract:

The fully connected conditional random field (CRF) with Gaussian pairwise potentials has proven popular and effective for multi-class semantic segmentation. While the energy of a dense CRF can be minimized accurately using a linear programming (LP) relaxation, the state-of-the-art algorithm is too slow to be useful in practice. To alleviate this deficiency, we introduce an efficient LP minimization algorithm for dense CRFs. To this end, we develop a proximal minimization framework, where the ...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted manuscript

Actions


Access Document


Files:
Publisher copy:
10.1109/CVPR.2017.313

Authors


More by this author
Department:
Lady Margaret Hall
Ajanthan, T More by this author
More by this author
Department:
Oxford, MPLS, Engineering Science
Salzmann, M More by this author
Expand authors...
Australian Department of Broadband, Communications and the Digital Economy More from this funder
Expand funders...
Publisher:
Institute of Electrical and Electronics Engineers Publisher's website
Publication date:
2017-07-08
Acceptance date:
2017-03-03
DOI:
Pubs id:
pubs:707604
URN:
uri:4120842d-d115-4f2c-bb5a-99b3285653bc
UUID:
uuid:4120842d-d115-4f2c-bb5a-99b3285653bc
Local pid:
pubs:707604

Terms of use


Metrics



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

TO TOP