A Study for Semi-supervised Learning with Random Erasing

Yuuhi Okahana, Yusuke Gotoh

研究成果

抄録

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.

本文言語English
ホスト出版物のタイトルLecture Notes on Data Engineering and Communications Technologies
出版社Springer Science and Business Media Deutschland GmbH
ページ478-490
ページ数13
DOI
出版ステータスPublished - 2020

出版物シリーズ

名前Lecture Notes on Data Engineering and Communications Technologies
47
ISSN(印刷版)2367-4512
ISSN(電子版)2367-4520

ASJC Scopus subject areas

  • メディア記述
  • 電子工学および電気工学
  • コンピュータ サイエンスの応用
  • コンピュータ ネットワークおよび通信
  • 情報システム

フィンガープリント

「A Study for Semi-supervised Learning with Random Erasing」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル