Image Annotation and Retrieval Using Dual Classifier Formulation
| Author(s) | : | PranavkumarR.Joshi, RiddhiV.Shah |
| Institution | : | DepartmentofElectronics and Communication, EngineeringParulInstitute of Engineering and Technology, Limda,Vadodara |
| Published In | : | Vol. 2, Issue 5 — May 2015 |
| Page No. | : | 424-426 |
| Domain | : | Engineering |
| Type | : | Research Paper |
| ISSN (Online) | : | 2348-4470 |
| ISSN (Print) | : | 2348-6406 |
Automatic image annotation is a difficult and highly relevant machine learningtask.Recentadvanceshavesignificantlyimprovedthestate-of-the-art inretrievalaccuracy withalgorithmsbasedonnearestneighborclassification incarefullylearnedmetric spaces. Butthis comesatapriceofincreasedcomputationalcomplexityduringtrainingand testing.WeproposeFastTag,anovelalgorithmthatachievescomparableresultswithtwosimplelinearmappingsthat arecoregularizedinajointconvexlossfunction. The lossfunctioncanbeefficientlyoptimized inclosedformup-dates,whichallowsustoincorporatealargenumberofimagedescriptorscheaply.Onseveralstandard real-worldbenchmark data sets, wedemonstratethat FastTagmatches thecurrentstate-of-the-artintaggingqual-ity,yetreduces the trainingand testingtimesbyseveralordersofmagnitudeand haslowerasymptoticcomplexity
PranavkumarR.Joshi, RiddhiV.Shah, “Image Annotation and Retrieval Using Dual Classifier Formulation”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 2, Issue 5, pp. 424-426, May 2015.
