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

Yanling Tian, Weitong Zhang, Qieshi Zhang, Gang Lu

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

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings of the International MultiConference of Engineers and Computer Scientists 2018, IMECS 2018
EditorsS. I. Ao, Craig Douglas, David Dagan Feng, Korsunsky Korsunsky, Oscar Castillo
PublisherNewswood Limited
Pages334-338
Number of pages5
ISBN (Electronic)9789881404787
Publication statusPublished - 2018
Externally publishedYes
Event2018 International MultiConference of Engineers and Computer Scientists, IMECS 2018 - Hong Kong, Hong Kong
Duration: 2018 Mar 142018 Mar 16

Publication series

NameLecture Notes in Engineering and Computer Science
Volume2233
ISSN (Print)2078-0958

Other

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

Keywords

  • CNN
  • Indoor scene
  • Multi-label
  • Scene classification

ASJC Scopus subject areas

  • Computer Science (miscellaneous)

Fingerprint Dive into the research topics of 'Inception classification and object detection based joint-cnn for indoor scene classification'. Together they form a unique fingerprint.

  • Cite this

    Tian, Y., Zhang, W., Zhang, Q., & Lu, G. (2018). Inception classification and object detection based joint-cnn for indoor scene classification. In S. I. Ao, C. Douglas, D. D. Feng, K. Korsunsky, & O. Castillo (Eds.), Proceedings of the International MultiConference of Engineers and Computer Scientists 2018, IMECS 2018 (pp. 334-338). (Lecture Notes in Engineering and Computer Science; Vol. 2233). Newswood Limited.