Annual Conference of KIPS (한국정보처리학회:학술대회논문집)

  • 2019.10a
  • /
  • Pages.1004-1006
  • /
  • 2019
  • /
  • 2005-0011(pISSN)
  • /
  • 2671-7298(eISSN)
Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Understanding the Effect of Different Scale Information Fusion in Deep Convolutional Neural Networks

딥 CNN에서의 Different Scale Information Fusion (DSIF)의 영향에 대한 이해

  • Liu, Kai (Department of Computer Engineering, Sejong University) ;
  • Cheema, Usman (Department of Computer Engineering, Sejong University) ;
  • Moon, Seungbin (Department of Computer Engineering, Sejong University)
  • Published : 2019.10.30
Download PDF
⟨ Previous Next ⟩

Abstract

Different scale of information is an important component in computer vision systems. Recently, there are considerable researches on utilizing multi-scale information to solve the scale-invariant problems, such as GoogLeNet and FPN. In this paper, we introduce the notion of different scale information fusion (DSIF) and show that it has a significant effect on the performance of object recognition systems. We analyze the DSIF in several architecture designs, and the effect of nonlinear activations, dropout, sub-sampling and skip connections on it. This leads to clear suggestions for ways of the DSIF to choose.

Keywords