Learning categories from few examples with multi model knowledge transfer

Tatiana Tommasi, Francesco Orabona, Barbara Caputo

Research output: Contribution to journalArticlepeer-review

126 Scopus citations


Learning a visual object category from few samples is a compelling and challenging problem. In several real-world applications collecting many annotated data is costly and not always possible. However, a small training set does not allow to cover the high intraclass variability typical of visual objects. In this condition, machine learning methods provide very few guarantees. This paper presents a discriminative model adaptation algorithm able to proficiently learn a target object with few examples by relying on other previously learned source categories. The proposed method autonomously chooses from where and how much to transfer information by solving a convex optimization problem which ensures to have the minimal leave-one-out error on the available training set. We analyze several properties of the described approach and perform an extensive experimental comparison with other existing transfer solutions, consistently showing the value of our algorithm. © 2013 IEEE.
Original languageEnglish (US)
Pages (from-to)928-941
Number of pages14
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number5
StatePublished - Jan 1 2014
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2023-09-25

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Software
  • Applied Mathematics
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Learning categories from few examples with multi model knowledge transfer'. Together they form a unique fingerprint.

Cite this