Zero shot deep learning from semantic attributes

Philippe M. Burlina, Aurora C. Schmidt, I. Jeng Wang

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

Abstract

We study the problem of classifying images when no training exemplars are available for some image classes, and therefore direct classification is not possible. We use instead semantic attributes: if attributes of yet unseen classes can be determined, then class labels may themselves be decided based on prior knowledge of class to attributes relationships. We present several methods for determining attributes, including (A) an approach based on attribute classifiers, and approaches using (B) MAP and (C) MMSE attribute estimators using image classifiers for known classes. Preliminary tests obtained using a dataset comprised of ImageNet images and Human218 attributes yield encouraging performance.

Original languageEnglish (US)
Title of host publicationProceedings - 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages871-876
Number of pages6
ISBN (Electronic)9781509002870
DOIs
StatePublished - Mar 2 2016
EventIEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015 - Miami, United States
Duration: Dec 9 2015Dec 11 2015

Publication series

NameProceedings - 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015

Other

OtherIEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015
Country/TerritoryUnited States
CityMiami
Period12/9/1512/11/15

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Zero shot deep learning from semantic attributes'. Together they form a unique fingerprint.

Cite this