Knowledge transfer with interactive learning of semantic relationships

Jonghyun Choi, Sung Ju Hwang, Leonid Sigal, Larry S. Davis

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

7 Citations (Scopus)

Abstract

We propose a novel learning framework for object categorization with interactive semantic feedback. In this framework, a discriminative categorization model improves through human-guided iterative semantic feedbacks. Specifically, the model identifies the most helpful relational semantic queries to discriminatively refine the model. The user feedback on whether the relationship is semantically valid or not is incorporated back into the model, in the form of regularization, and the process iterates. We validate the proposed model in a few-shot multi-class classification scenario, where we measure classification performance on a set of 'target' classes, with few training instances, by leveraging and transferring knowledge from 'anchor' classes, that contain larger set of labeled instances.

Original languageEnglish
Title of host publication30th AAAI Conference on Artificial Intelligence, AAAI 2016
PublisherAAAI press
Pages1505-1511
Number of pages7
ISBN (Electronic)9781577357605
Publication statusPublished - 2016
Event30th AAAI Conference on Artificial Intelligence, AAAI 2016 - Phoenix, United States
Duration: 2016 Feb 122016 Feb 17

Publication series

Name30th AAAI Conference on Artificial Intelligence, AAAI 2016

Other

Other30th AAAI Conference on Artificial Intelligence, AAAI 2016
Country/TerritoryUnited States
CityPhoenix
Period16/2/1216/2/17

Bibliographical note

Funding Information:
J. Choi and L.S. Davis were partially supported by MURI from the Office of Naval Research under the Grant N00014- 10-1-0934.

Publisher Copyright:
© 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Knowledge transfer with interactive learning of semantic relationships'. Together they form a unique fingerprint.

Cite this