Learning object models from few examples

Ishan Misra, Yuxiong Wang, Martial Hebert

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Current computer vision systems rely primarily on fixed models learned in a supervised fashion, i.e., with extensive manually labelled data. This is appropriate in scenarios in which the information about all the possible visual queries can be anticipated in advance, but it does not scale to scenarios in which new objects need to be added during the operation of the system, as in dynamic interaction with UGVs. For example, the user might have found a new type of object of interest, e.g., a particular vehicle, which needs to be added to the system right away. The supervised approach is not practical to acquire extensive data and to annotate it. In this paper, we describe techniques for rapidly updating or creating models using sparsely labelled data. The techniques address scenarios in which only a few annotated training samples are available and need to be used to generate models suitable for recognition. These approaches are crucial for on-the-fly insertion of models by users and on-line learning.

Original languageEnglish (US)
Title of host publicationUnmanned Systems Technology XVIII
EditorsRobert E. Karlsen, Grant R. Gerhart, Douglas W. Gage, Charles M. Shoemaker
ISBN (Electronic)9781510600782
StatePublished - 2016
Externally publishedYes
EventUnmanned Systems Technology XVIII - Baltimore, United States
Duration: Apr 20 2016Apr 21 2016

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X


ConferenceUnmanned Systems Technology XVIII
Country/TerritoryUnited States


  • Ground robots
  • Learning
  • Object recognition

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Learning object models from few examples'. Together they form a unique fingerprint.

Cite this