Latent-Space Data Augmentation for Visually-Grounded Language Understanding

Aly Magassouba, Komei Sugiura, Hisashi Kawai

研究成果: Conference contribution

抄録

This is an extension from a selected paper from JSAI2019. In this paper, we study data augmentation for visually-grounded language understanding in the context of picking task. A typical picking task consists of predicting a target object specified by an ambiguous instruction,e.g., “Pick up the yellow toy near the bottle”. We specifically show that existing methods for understanding such an instruction can be improved by data augmentation. More explicitly, MCTM [1] and MTCM-GAN [2] show better results with data augmentation when specifically considering latent space features instead of raw features. Additionally our results show that latent-space data augmentation can improve better a network accuracy than regularization methods.

本文言語English
ホスト出版物のタイトルAdvances in Artificial Intelligence - Selected Papers from the Annual Conference of Japanese Society of Artificial Intelligence JSAI 2019
編集者Yukio Ohsawa, Katsutoshi Yada, Takayuki Ito, Yasufumi Takama, Eri Sato-Shimokawara, Akinori Abe, Junichiro Mori, Naohiro Matsumura
出版社Springer
ページ179-187
ページ数9
ISBN(印刷版)9783030398774
DOI
出版ステータスPublished - 2020
外部発表はい
イベント33rd Annual Conference of the Japanese Society for Artificial Intelligence, JSAI 2019 - Niigata, Japan
継続期間: 2019 6月 42019 6月 7

出版物シリーズ

名前Advances in Intelligent Systems and Computing
1128 AISC
ISSN(印刷版)2194-5357
ISSN(電子版)2194-5365

Conference

Conference33rd Annual Conference of the Japanese Society for Artificial Intelligence, JSAI 2019
国/地域Japan
CityNiigata
Period19/6/419/6/7

ASJC Scopus subject areas

  • 制御およびシステム工学
  • コンピュータ サイエンス(全般)

フィンガープリント

「Latent-Space Data Augmentation for Visually-Grounded Language Understanding」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