Source model selection for transfer learning of image classification using supervised contrastive loss

Young Seong Cho, Samuel Kim, Jee Hyong Lee

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

4 Scopus citations

Abstract

Transfer learning is a framework that improves performance of target task by transferring knowledge from training source task. As deep learning research accumulate, more source models can be easily obtained. In time series domain, the Mean Silhouette Coefficient of the set of feature vectors which forward propagated through source models is used to select the best source model performs target task. But for image classification, the model which is better at generalization could have the lower coefficient. To adjust this, we propose to use another measure, Supervised Contrastive Loss. In this work, we evaluate which measure is better to select the best model. We present the superiority of using the supervised contrastive loss through the comparative experiment.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE International Conference on Big Data and Smart Computing, BigComp 2021
EditorsHerwig Unger, Jinho Kim, U Kang, Chakchai So-In, Junping Du, Walid Saad, Young-guk Ha, Christian Wagner, Julien Bourgeois, Chanboon Sathitwiriyawong, Hyuk-Yoon Kwon, Carson Leung
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages325-329
Number of pages5
ISBN (Electronic)9781728189246
DOIs
StatePublished - Jan 2021
Event2021 IEEE International Conference on Big Data and Smart Computing, BigComp 2021 - Jeju Island, Korea, Republic of
Duration: 17 Jan 202120 Jan 2021

Publication series

NameProceedings - 2021 IEEE International Conference on Big Data and Smart Computing, BigComp 2021

Conference

Conference2021 IEEE International Conference on Big Data and Smart Computing, BigComp 2021
Country/TerritoryKorea, Republic of
CityJeju Island
Period17/01/2120/01/21

Keywords

  • Contrastive Learning
  • Deep Learning
  • Image Classification
  • Model Selection
  • Transfer Learning

Fingerprint

Dive into the research topics of 'Source model selection for transfer learning of image classification using supervised contrastive loss'. Together they form a unique fingerprint.

Cite this