Show simple item record

dc.contributor.authorScheirer, Walter Jerome
dc.contributor.authorAnthony, Samuel English
dc.contributor.authorNakayama, Ken
dc.contributor.authorCox, David Daniel
dc.date.accessioned2014-04-25T16:46:06Z
dc.date.issued2014
dc.identifier.citationScheirer, Walter, Samuel Anthony, Ken Nakayama, and David Cox. 2014. Perceptual annotation: measuring human vision to improve computer vision. IEEE Transactions on Pattern Analysis and Machine Intelligence PP(99): 1–8.en_US
dc.identifier.issn0162-8828en_US
dc.identifier.urihttp://nrs.harvard.edu/urn-3:HUL.InstRepos:12111387
dc.description.abstractFor many problems in computer vision, human learners are considerably better than machines. Humans possess highly accurate internal recognition and learning mechanisms that are not yet understood, and they frequently have access to more extensive training data through a lifetime of unbiased experience with the visual world. We propose to use visual psychophysics to directly leverage the abilities of human subjects to build better machine learning systems. First, we use an advanced online psychometric testing platform to make new kinds of annotation data available for learning. Second, we develop a technique for harnessing these new kinds of information – “perceptual annotations” – for support vector machines. A key intuition for this approach is that while it may remain infeasible to dramatically increase the amount of data and high-quality labels available for the training of a given system, measuring the exemplar-by-exemplar difficulty and pattern of errors of human annotators can provide important information for regularizing the solution of the system at hand. A case study for the problem face detection demonstrates that this approach yields state-ofthe- art results on the challenging FDDB data set.en_US
dc.description.sponsorshipEngineering and Applied Sciencesen_US
dc.description.sponsorshipMolecular and Cellular Biologyen_US
dc.language.isoen_USen_US
dc.publisherInstitute of Electrical & Electronics Engineers (IEEE)en_US
dc.relation.isversionofdoi:10.1109/tpami.2013.2297711en_US
dc.relation.hasversionhttp://www.coxlab.org/pdfs/2014_scheirer_tpami.pdfen_US
dash.licenseOAP
dc.subjectmachine learningen_US
dc.subjectcitizen scienceen_US
dc.subjectface detectionen_US
dc.subjectpsychologyen_US
dc.subjectpsychometricsen_US
dc.subjectpsychophysicsen_US
dc.subjectregularizationen_US
dc.subjectsupport vector machinesen_US
dc.subjectvisual recognitionen_US
dc.titlePerceptual Annotation: Measuring Human Vision to Improve Computer Visionen_US
dc.typeJournal Articleen_US
dc.description.versionAccepted Manuscripten_US
dc.relation.journalIEEE Transactions on Pattern Analysis and Machine Intelligenceen_US
dash.depositing.authorCox, David Daniel
dc.date.available2014-04-25T16:46:06Z
dc.identifier.doi10.1109/tpami.2013.2297711*
dash.contributor.affiliatedScheirer, Walter
dash.contributor.affiliatedAnthony, Samuel English
dash.contributor.affiliatedCox, David
dash.contributor.affiliatedNakayama, Ken


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record