One-shot categorization of novel object classes in humans.

One aspect of human vision unmatched by machines is the capacity to generalize from few samples. Observers tend to know when novel objects are in the same class despite large differences in shape, material or viewpoint. A major challenge in studying such generalization is that participants can see e...

Descripción completa

Detalles Bibliográficos
Publicado en:Vision Research Vol. 165; pp. 98 - 109
Autores principales: Morgenstern, Yaniv, Schmidt, Filipp, Fleming, Roland W.
Formato: research Journal Article
Publicado: Pergamon Press - An Imprint of Elsevier Science Dec2019
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=141774562&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 141774562
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        00426989
        2FL
      jtl: Vision Research
      issn: 00426989
      maglogo: N
    pubinfo:
      dt: Dec2019
      vid: 165
      pid: 2410
      pub: Pergamon Press - An Imprint of Elsevier Science
    artinfo:
      ui:
        141774562
        141774562
        NLM31707254
        141774562
        10.1016/j.visres.2019.09.005
        NLM31707254
        141774562
      ppf: 98
      ppct: 11
      formats:
      tig:
        atl: One-shot categorization of novel object classes in humans.
      aug:
        au:
          Morgenstern, Yaniv
          Schmidt, Filipp
          Fleming, Roland W.
        affil: Department of Experimental Psychology, Justus-Liebig University Giessen, Giessen 35394, Germany
      sug:
        subj:
          Visual Perception Physiology
          Attention
          Perception
          Human
          Physical Stimulation Methods
          Comparative Studies
          Multicenter Studies
          Evaluation Research
          Validation Studies
      ab: One aspect of human vision unmatched by machines is the capacity to generalize from few samples. Observers tend to know when novel objects are in the same class despite large differences in shape, material or viewpoint. A major challenge in studying such generalization is that participants can see each novel sample only once. To overcome this, we used crowdsourcing to obtain responses from 500 human observers on 20 novel object classes, with each stimulus compared to 1 or 16 related objects. The results reveal that humans generalize from sparse data in highly systematic ways with the number and variance of the samples. We compared human responses to 'ShapeComp', an image-computable model based on >100 shape descriptors, and 'AlexNet', a convolution neural network that roughly matches humans at recognizing 1000 categories of real-world objects. With 16 samples, the models were consistent with human responses without free parameters. Thus, when there are a sufficient number of samples, observers rely on shallow but efficient processes based on a fixed set of features. With 1 sample, however, the models required different feature weights for each object. This suggests that one-shot categorization involves more sophisticated processes that actively identify the unique characteristics underlying each object class.
      pubtype: Academic Journal
      doctype:
        research
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N