Heterogeneous data integration using confidence estimation of unseen visual data for zero-shot learning

Sanghyun Seo, Juntae Kim

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Zero-shot learning is a learning methodology that can be used to recognize concepts that have never been seen during the training phase. Recently, interest in zero-shot learning has been increased by embedding multi-modal data into common vector space through heterogeneous data integration methodology. However, since the existing methodologies compare heterogeneous data focusing on the similarity between each vector, the performance of zero-shot learning decreases when the number of semantic candidates increases. We propose a heterogeneous data integration methodology using a confidence estimator for unseen visual data which estimates that whether input data is unseen data or not and output confidence measure. The proposed methodology constructs a more efficient zero-shot learning model by applying estimated confidence of input unseen visual data to the visual-semantic distance obtained from heterogeneous data integration model. Experiments have shown that the proposed methodology can improve zero-shot learning performance for unseen data despite a small performance decrease in the seen data.

Original languageEnglish
Title of host publicationProceedings of the 2019 2nd International Conference on Software Engineering and Information Management, ICSIM 2019 - Workshop 2019 2nd International Conference on Big Data and Smart Computing, ICBDSC 2019
PublisherAssociation for Computing Machinery
Pages171-174
Number of pages4
ISBN (Electronic)9781450366427
DOIs
StatePublished - 10 Jan 2019
Event2nd International Conference on Software Engineering and Information Management, ICSIM 2019 - and its Workshop 2019 2nd International Conference on Big Data and Smart Computing, ICBDSC 2019 - Bali, Indonesia
Duration: 10 Jan 201913 Jan 2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2nd International Conference on Software Engineering and Information Management, ICSIM 2019 - and its Workshop 2019 2nd International Conference on Big Data and Smart Computing, ICBDSC 2019
Country/TerritoryIndonesia
CityBali
Period10/01/1913/01/19

Keywords

  • Confidence estimation
  • Cross modal retrieval
  • Heterogeneous data integration
  • Visual semantic embedding
  • Zero-shot learning

Fingerprint

Dive into the research topics of 'Heterogeneous data integration using confidence estimation of unseen visual data for zero-shot learning'. Together they form a unique fingerprint.

Cite this