Journal article icon

Journal article

Revisiting deep structured models for pixel-level labeling with gradient-based inference

Abstract:

Semantic segmentation and other pixel-level labeling tasks have made significant progress recently due to the deep learning paradigm. Many state-of-the-art structured prediction methods also include a random field model with a hand-crafted Gaussian potential to model spatial priors and label consistencies and feature-based image conditioning. These random field models with image conditioning typically require computationally demanding filtering techniques during inference. In this paper, we p...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1137/18m1167267

Authors


More by this author
Role:
Author
ORCID:
0000-0003-3137-1405
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
Publisher:
Society for Industrial & Applied Mathematics Publisher's website
Journal:
SIAM Journal on Imaging Sciences Journal website
Volume:
11
Issue:
4
Pages:
2610-2628
Publication date:
2018-11-06
Acceptance date:
2018-08-27
DOI:
ISSN:
1936-4954
Language:
English
Keywords:
Pubs id:
pubs:981347
UUID:
uuid:07172dfd-e81e-435c-a810-1b193de2734d
Local pid:
pubs:981347
Source identifiers:
981347
Deposit date:
2019-03-12

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