Presentation information

General Session

General Session » GS-7 Vision, speech media processing

[4I3-GS-7d] 画像音声メディア処理:画像理解

Fri. Jun 11, 2021 1:40 PM - 3:20 PM Room I (GS room 4)

座長:吉田 周平(NEC)

1:40 PM - 2:00 PM

[4I3-GS-7d-01] Shape biased learning using style transfer for improving accuracy of Illustration recognition

〇Jeffrey Kougo1, Takayuki Watanabe1, Junji Yamato1, Hirotoshi Taira2, Hiromi Narimatsu3, Hiroaki Sugiyama3 (1. Kogakuin University, 2. Osaka Institute of Technology, 3. NTT Communication Science Laboratories)

Keywords:Image understanding, Illustration image recognition, Style transfer

Illustration images, such as those used as options in English exam questions, tend to have lower accuracy than photographs in object recognition using CNN, etc. It has been pointed out that CNN learns more texture than shape in object recognition, which is presumably an obstacle to improving the recognition rate of illustration images. In this study, we tried a method that inhibits the learning of texture information by synthesizing various textures for object images of the same shape utilizing style transition, promoting the learning of shape information, and confirmed the improvement of the recognition rate of illustration images.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.