Transfer Learning using Transformation: Is Large Unlabeled Data Helpful at Segmentation?

Heejeong Lim, Seongwook Yoon, Sanghoon Sull

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

Abstract

We propose a simple method of transfer learning for image segmentation. Creating labeled data for deep neural network training in image segmentation is particularly expensive than other tasks. Hence, practically, the labeled data is much less than the unlabeled data. So, we introduce a method that is helpful for segmentation by using unlabeled data. Our key is the RGB-to-HSV transformation and we use it in two ways. The first way is to pre-train a network to work as an RGB-to-HSV transformer which can extract useful features, and transfer the pre-trained weights to another network for segmentation, which is one of the most common transfer learning method. The second way is to provide additional information to the segmented network by providing HSV, the output of the pre-trained network, as additional input. We performed several experiments about our proposal using Cityscapes dataset.

Original languageEnglish
Title of host publicationICTC 2020 - 11th International Conference on ICT Convergence
Subtitle of host publicationData, Network, and AI in the Age of Untact
PublisherIEEE Computer Society
Pages387-390
Number of pages4
ISBN (Electronic)9781728167589
DOIs
Publication statusPublished - 2020 Oct 21
Event11th International Conference on Information and Communication Technology Convergence, ICTC 2020 - Jeju Island, Korea, Republic of
Duration: 2020 Oct 212020 Oct 23

Publication series

NameInternational Conference on ICT Convergence
Volume2020-October
ISSN (Print)2162-1233
ISSN (Electronic)2162-1241

Conference

Conference11th International Conference on Information and Communication Technology Convergence, ICTC 2020
Country/TerritoryKorea, Republic of
CityJeju Island
Period20/10/2120/10/23

Keywords

  • HSV transformation
  • Image segmentation
  • Transfer learning

ASJC Scopus subject areas

  • Information Systems
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Transfer Learning using Transformation: Is Large Unlabeled Data Helpful at Segmentation?'. Together they form a unique fingerprint.

Cite this