Efficient Learning to Label Images

dc.contributor.authorJia, Ke
dc.contributor.authorCheng, Li
dc.contributor.authorLiu, Nianjun
dc.contributor.authorWang, Lei
dc.coverage.spatialSan Francisco USA
dc.date.accessioned2015-12-07T22:23:50Z
dc.date.createdJune 13-18 2010
dc.date.issued2010
dc.date.updated2016-02-24T11:29:55Z
dc.description.abstractConditional random field methods (CRFs) have gained popularity for image labeling tasks in recent years. In this paper, we describe an alternative discriminative approach, by extending the large margin principle to incorporate spatial correlations among neighboring pixels. In particular, by explicitly enforcing the submodular condition, graph-cuts is conveniently integrated as the inference engine to attain the optimal label assignment efficiently. Our approach allows learning a model with thousands of parameters, and is shown to be capable of readily incorporating higher-order scene context. Empirical studies on a variety of image datasets suggest that our approach performs competitively compared to the state-of-the-art scene labeling methods.
dc.identifier.isbn9781424469857
dc.identifier.urihttp://hdl.handle.net/1885/20889
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE Inc)
dc.relation.ispartofseriesComputer Vision and Pattern Recognition Conference (CVPR 2010)
dc.sourceProceedings of The 23rd IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010)
dc.subjectKeywords: Conditional random field; Discriminative approach; Efficient learning; Empirical studies; Graph-cuts; Higher order; Image datasets; Image labeling; Label images; Labeling methods; Large margin principle; Spatial correlations; Submodular; Pattern recogniti
dc.titleEfficient Learning to Label Images
dc.typeConference paper
local.bibliographicCitation.startpage4
local.contributor.affiliationJia, Ke, College of Engineering and Computer Science, ANU
local.contributor.affiliationCheng, Li, Toyota Technological Institute at Chicago (TTI)
local.contributor.affiliationLiu, Nianjun, College of Engineering and Computer Science, ANU
local.contributor.affiliationWang, Lei, College of Engineering and Computer Science, ANU
local.contributor.authoremailrepository.admin@anu.edu.au
local.contributor.authoruidJia, Ke, u4326094
local.contributor.authoruidLiu, Nianjun, u1814805
local.contributor.authoruidWang, Lei, u4259382
local.description.embargo2037-12-31
local.description.notesImported from ARIES
local.description.refereedYes
local.identifier.absfor080104 - Computer Vision
local.identifier.absseo970109 - Expanding Knowledge in Engineering
local.identifier.ariespublicationu4963866xPUB14
local.identifier.doi10.1109/ICPR.2010.236
local.identifier.scopusID2-s2.0-78149491985
local.identifier.uidSubmittedByu4963866
local.type.statusPublished Version

Downloads

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
01_Jia_Efficient_Learning_to_Label_2010.pdf
Size:
362.72 KB
Format:
Adobe Portable Document Format
Back to topicon-arrow-up-solid
 
APRU
IARU
 
edX
Group of Eight Member

Acknowledgement of Country

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.


Contact ANUCopyrightDisclaimerPrivacyFreedom of Information

+61 2 6125 5111 The Australian National University, Canberra

TEQSA Provider ID: PRV12002 (Australian University) CRICOS Provider Code: 00120C ABN: 52 234 063 906