Dataset Issues in Object Recognition
21 pages
English

Dataset Issues in Object Recognition

Obtenez un accès à la bibliothèque pour le consulter en ligne
En savoir plus
21 pages
English
Obtenez un accès à la bibliothèque pour le consulter en ligne
En savoir plus

Description

Niveau: Supérieur, Doctorat, Bac+8
Dataset Issues in Object Recognition J. Ponce1,2, T.L. Berg3, M. Everingham4, D.A. Forsyth1, M. Hebert5, S. Lazebnik1, M. Marszalek6, C. Schmid6, B.C. Russell7, A. Torralba7, C.K.I. Williams8, J. Zhang6, and A. Zisserman4 1 University of Illinois at Urbana-Champaign, USA 2 Ecole Normale Superieure, Paris, France 3 University of California at Berkeley, USA 4 Oxford University, UK 5 Carnegie Mellon University, Pittsburgh, USA 6 INRIA Rhone-Alpes, Grenoble, France 7 MIT, Cambridge, USA 8 University of Edinburgh, Edinburgh, UK Abstract. Appropriate datasets are required at all stages of object recognition research, including learning visual models of object and scene categories, detecting and localizing instances of these models in im- ages, and evaluating the performance of recognition algorithms. Current datasets are lacking in several respects, and this paper discusses some of the lessons learned from existing e?orts, as well as innovative ways to obtain very large and diverse annotated datasets. It also suggests a few criteria for gathering future datasets. 1 Introduction Image databases are an essential element of object recognition research. They are required for learning visual object models and for testing the performance of classification, detection, and localization algorithms.

  • multiple algorithms currently

  • per image

  • current datasets

  • fei-fei li

  • datasets avail- able

  • recent recognition

  • recognition algorithms

  • intra-class variability


Sujets

Informations

Publié par
Nombre de lectures 15
Langue English
Poids de l'ouvrage 3 Mo

Exrait

DatasetIssuesinObjectRecognition1J.Ponce1,2,T.L.Berg3,M.Everingham4,D.A.Forsyth1,M.Hebert5,S.Lazebnik1,M.Marszalek6,C.Schmid6,B.C.Russell7,A.Torralba7,C.K.I.Williams8,J.Zhang6,andA.Zisserman4UniversityofIllinoisatUrbana-Champaign,USA2EcoleNormaleSup´erieure,Paris,France3UniversityofCaliforniaatBerkeley,USA4OxfordUniversity,UKCarnegieMellonUniversity,Pittsburgh,USAINRIARhoˆne-Alpes,Grenoble,France7MIT,Cambridge,USAUniversityofEdinburgh,Edinburgh,UK586Abstract.Appropriatedatasetsarerequiredatallstagesofobjectrecognitionresearch,includinglearningvisualmodelsofobjectandscenecategories,detectingandlocalizinginstancesofthesemodelsinim-ages,andevaluatingtheperformanceofrecognitionalgorithms.Currentdatasetsarelackinginseveralrespects,andthispaperdiscussessomeofthelessonslearnedfromexistingefforts,aswellasinnovativewaystoobtainverylargeanddiverseannotateddatasets.Italsosuggestsafewcriteriaforgatheringfuturedatasets.1IntroductionImagedatabasesareanessentialelementofobjectrecognitionresearch.Theyarerequiredforlearningvisualobjectmodelsandfortestingtheperformanceofclassification,detection,andlocalizationalgorithms.Infact,publiclyavailableimagecollectionssuchasUIUC[1],Caltech4[10],andCaltech101[9]haveplayedakeyroleintherecentresurgenceofcategory-levelrecognitionresearch,drivingthefieldbyprovidingacommongroundforalgorithmdevelopmentandevaluation.Currentdatasets,however,offerasomewhatlimitedrangeofimagevariability:Althoughtheappearance(andtosomeextent,theshape)ofobjectsdoesindeedvarywithineachclass(e.g.,amongtheairplanes,cars,faces,andmotorbikesofCaltech4),theviewpointsandorientationsofdifferentinstancesineachcategorytendtobesimilar(e.g.,sideviewsofcarstakenbyahorizontalcamerainUIUC);theirsizesandimagepositionsarenormalized(e.g.,theobjectsofinteresttakeupmostoftheimageandareapproximatelycenteredinCaltech101);thereisonlyoneinstanceofanobjectperimage;finally,thereislittleornoocclusionandbackgroundclutter.ThisisillustratedbyFigures1and3fortheCaltech101database,butremainstrueofmostdatasetsavailabletoday.Theproblemswithsuchrestrictionsaretwofold:(i)somealgorithmsmayexploitthem(forexamplenear-globaldescriptorswithnoscaleorrotationin-variancemayperformwellonsuchimages),yetwillfailwhentherestrictions
2Fi.g.1SampleimagesrfmoehtCaltech101dataset,]9[courtesyfo-ieFieFL.i
  • Accueil Accueil
  • Univers Univers
  • Ebooks Ebooks
  • Livres audio Livres audio
  • Presse Presse
  • BD BD
  • Documents Documents