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
Authors
Funding
Bibliographic Details
- 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
Item Description
- 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
- Copyright holder:
- Society for Industrial and Applied Mathematics
- Copyright date:
- 2018
- Notes:
- © 2018, Society for Industrial and Applied Mathematics
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record