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.
|Title of host publication||2020 17th International Conference on Ubiquitous Robots, UR 2020|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||4|
|Publication status||Published - 2020 Jun|
|Event||17th International Conference on Ubiquitous Robots, UR 2020 - Kyoto, Japan|
Duration: 2020 Jun 22 → 2020 Jun 26
|Name||2020 17th International Conference on Ubiquitous Robots, UR 2020|
|Conference||17th International Conference on Ubiquitous Robots, UR 2020|
|Period||20/6/22 → 20/6/26|
Bibliographical noteFunding 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).
© 2020 IEEE.
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Mechanical Engineering
- Control and Optimization