Is Whole Object Information Helpful for Scene Recognition?

Hongje Seong, Junhyuk Hyun, Euntai Kim

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

Abstract

Scene recognition is one of the visual tasks, classifying a place category on an image. Scene images may contain various objects, and these objects tend to become clues to recognize the scene of the image. Therefore, many previous approaches for scene recognition use the object information that appeared in the image to improve the performance. Here, we raise a question of whether whole object information is helpful for scene recognition. To find the answer to the question, we conduct experiments on Places365, which is the largest scene recognition dataset consist of real-world images. To find the object classes which disturbed scene recognition, we utilize the Class Conversion Matrix, which is a deep learning approach. Finally, we found that some object classes may contribute to disturbing scene recognition. It indicates that not only making good use of object information, but also dropping disturbed object information is also important.

Original languageEnglish
Title of host publication2020 17th International Conference on Ubiquitous Robots, UR 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages149-152
Number of pages4
ISBN (Electronic)9781728157153
DOIs
Publication statusPublished - 2020 Jun
Event17th International Conference on Ubiquitous Robots, UR 2020 - Kyoto, Japan
Duration: 2020 Jun 222020 Jun 26

Publication series

Name2020 17th International Conference on Ubiquitous Robots, UR 2020

Conference

Conference17th International Conference on Ubiquitous Robots, UR 2020
CountryJapan
CityKyoto
Period20/6/2220/6/26

Bibliographical note

Funding Information:
This research was supported by Next-Generation Information Computing Development Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Science, ICT (NRF-2017M3C4A7069370).

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Mechanical Engineering
  • Control and Optimization

Fingerprint Dive into the research topics of 'Is Whole Object Information Helpful for Scene Recognition?'. Together they form a unique fingerprint.

Cite this