Inception classification and object detection based joint-cnn for indoor scene classification

Yanling Tian, Weitong Zhang, Qieshi Zhang, Gang Lu

研究成果

1 被引用数 (Scopus)

抄録

While convolutional neural network (CNN) has been successfully used in many fields including single-label scene classification, it is vital to note that real world scenes generally contain multiple semantics and multi-label, especially in the indoor scene classification due to its content complexity. At the same time, most approaches try to make the network much deeper to make sure that they can extract more detail information. However, the deeper network will cause a lot of problems such as the increase of computational costs and network costs and so on. In order to solve these problems, this paper presents a novel framework which called Joint-CNN based on the proposed special label extraction and network structure. Extensive experiments on various data sets show that our method has enhanced the performance on MIT indoor67 and SUN397 data sets.

本文言語English
ホスト出版物のタイトルProceedings of the International MultiConference of Engineers and Computer Scientists 2018, IMECS 2018
編集者S. I. Ao, Craig Douglas, David Dagan Feng, Korsunsky Korsunsky, Oscar Castillo
出版社Newswood Limited
ページ334-338
ページ数5
ISBN(電子版)9789881404787
出版ステータスPublished - 2018
外部発表はい
イベント2018 International MultiConference of Engineers and Computer Scientists, IMECS 2018 - Hong Kong, Hong Kong
継続期間: 2018 3 142018 3 16

出版物シリーズ

名前Lecture Notes in Engineering and Computer Science
2233
ISSN(印刷版)2078-0958

Other

Other2018 International MultiConference of Engineers and Computer Scientists, IMECS 2018
国/地域Hong Kong
CityHong Kong
Period18/3/1418/3/16

ASJC Scopus subject areas

  • コンピュータ サイエンス(その他)

フィンガープリント

「Inception classification and object detection based joint-cnn for indoor scene classification」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