A Study for Semi-supervised Learning with Random Erasing

Yuuhi Okahana, Yusuke Gotoh

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Due to the recent popularization of various data classified by computer, machine learning is attracting great attention. A common method of machine learning is supervised learning, which classifies data using a large number of class labeled training data called labeled data. To improve the processing performance of supervised learning, it is effective to use Random Erasing in data augmentation. However, since supervised learning requires much labeled data, the cost of manually adding label information to an unclassified training case (unlabeled data) is very high. In this paper, we propose a method for achieving high classification accuracy using Random Erasing for semi-supervised learning using few labeled data and unlabeled data. In our evaluation, we confirm the availability of the proposed method compared with conventional methods.

Original languageEnglish
Title of host publicationLecture Notes on Data Engineering and Communications Technologies
PublisherSpringer
Pages478-490
Number of pages13
DOIs
Publication statusPublished - Jan 1 2020

Publication series

NameLecture Notes on Data Engineering and Communications Technologies
Volume47
ISSN (Print)2367-4512
ISSN (Electronic)2367-4520

    Fingerprint

ASJC Scopus subject areas

  • Media Technology
  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Computer Networks and Communications
  • Information Systems

Cite this

Okahana, Y., & Gotoh, Y. (2020). A Study for Semi-supervised Learning with Random Erasing. In Lecture Notes on Data Engineering and Communications Technologies (pp. 478-490). (Lecture Notes on Data Engineering and Communications Technologies; Vol. 47). Springer. https://doi.org/10.1007/978-3-030-39746-3_49