Matrix Completion for WeaklyWord文件下载.docx
- 文档编号:18683198
- 上传时间:2022-12-31
- 格式:DOCX
- 页数:14
- 大小:2.29MB
Matrix Completion for WeaklyWord文件下载.docx
《Matrix Completion for WeaklyWord文件下载.docx》由会员分享,可在线阅读,更多相关《Matrix Completion for WeaklyWord文件下载.docx(14页珍藏版)》请在冰豆网上搜索。
trainingimagesareannotatedwithasetofkeywordsdescribingtheircontents,butthevisualconceptsarenotexplicitlysegmentedintheimages.
formulatetheweakly-supervisedimageclassificationasalow-rankmatrixcompletionproblem.
三大优势:
(1)convex相较于multiple-instancelearningmethods.Weproposetwoalternativealgorithmsformatrixcompletion——MC-PosandMC-Simplex,motivatedbythemulti-labelimageclassificationproblemandtheadditivehistogramproperty
specificallytailoredtovisualdata,andprovetheirconvergence.
(2)isrobusttolabelingerrors,backgroundnoiseandpartialocclusions.
(3)beusedforsemanticsegmentation.Caneffectivelycapturingeachclassappearance.
Methods——imageclassificationandlocalizaionproblem
MIL-considerimagesasbagswithmanyinstancesdenotingpossibleregionsofinterest(BOWS)
drawbacks:
(1)castasaNP-hardbinaryquadraticproblem、leadtonon-convexmodels、highlysensibletoinitialization、heavilyrelyonanexplicitenumerationofinstances
(2)lackrobustnesstooutliers
(3)Uncleartobeextendedtousepartialinformation,suchasincompletelabelassignmentsormissingfeaturedescriptions.Forinstance,inFig.1aonetrainingimagehasnolabelforthecategorygrass.
Ourmethod——thehistogramofanentireimageisaweightedsumofthehistograminformationofallofitssubparts(tofactorizethehistogramofanimageasaweightedsumofclasshistograms(asmanyasobjectsarepresent)plusanerrortomodelthebackground.)
Usingthisproperty
webypassthecombinatorialnatureoffindingdesiredregionsineverypositiveimage
imageclassificationcanbeposedasarankminimizationproblem,sinceclasshistogramsaresharedacrossimages,andthenumberofclasshistogramsissmallcomparedtothenumberofimages.
amatrixcompletionframework.
1、ClassificationasaMatrixCompletionProblem
⑴theuseofmatrixcompletionforgeneralclassificationtasks
⑵useforweaklysupervisedmulti-labelimageclassificationandlocalization
BydirectlyestimatingC:
theappearanceofindividualclassescanberecoveredfromamulti-labeldatasetthusprovidethelocalizationforeachconceptintheimages.
2、NuclearNormasaConvexSurrogateoftheRankFunction——tominimize(rankisnon-convexandnon-differentiablefunction)
nuclearnorm——Z的奇异值的和
3、AddingRobustnessintoMatrixCompletion
TheresultingoptimizationproblemfindsthebestlabelassignmentYtstanderror
Matrices
suchthattherankofZisminimized,as
4、FixedPointContinuation(FPC)forMC-Pos/MC-Simplex
enjoythesameconvergencepropertiesoffixedpointcontinuation(FPC)methodsforrankminimizationwithoutconstraints.
Albeitconvex,thenuclearnormmakes(24)and(25)notsmooth.SincenuclearnormproblemsarenaturallycastasSemidefinitePrograms,existinginteriorpointmethodsareinapplicableduetothelargedimensionofZ.
FPC--
总结:
1、keyidea
histogramsoffullimagescontaintheinformationforpartscontainedtherein,soweaklysupervisedlearningcanbeformulatedasalow-rankproblemduetoitsaddivenature,andsolvedusingatransductivematrixcompletionframework
2、twonewconvexmethodsforperformingmulti-labelclassificationofhistogramdata,withprovenconvergenceproperties
3、abletofindclasshistogramrepresentationsandprovidelocalizationintheimages.
4、matrixcompletionallowsforhandlingofmissingdata,labelingerrors,backgroundnoiseandpartialocclusions
- 配套讲稿:
如PPT文件的首页显示word图标,表示该PPT已包含配套word讲稿。双击word图标可打开word文档。
- 特殊限制:
部分文档作品中含有的国旗、国徽等图片,仅作为作品整体效果示例展示,禁止商用。设计者仅对作品中独创性部分享有著作权。
- 关 键 词:
- Matrix Completion for Weakly