• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2023 Fiscal Year Final Research Report

Advancement of Deep Learning by Information Leakage

Research Project

  • PDF
Project/Area Number 21K11971
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 61010:Perceptual information processing-related
Research InstitutionMeijo University

Principal Investigator

HOTTA KAZUHIRO  名城大学, 理工学部, 教授 (40345426)

Project Period (FY) 2021-04-01 – 2024-03-31
Keywords深層学習 / 情報リーク
Outline of Final Research Achievements

I proposed a new approach based on information leakage to improve the accuracy of image recognition using deep learning. The effectiveness of the proposed method is demonstrated by experiments on various kinds of image datasets. The proposed method is applied to semantic segmentation that classifies all pixels in an image. Since semantic segmentation is demanded in cell biology, the effectiveness of the proposed method is also shown on cell images.

Free Research Field

画像認識

Academic Significance and Societal Importance of the Research Achievements

1つのネットワーク内もしくは他のネットワークから情報をリークすることにより深層学習の精度を改善させるという世界的にも新しい考え方を提案し、様々な画像データセットを用いた評価実験によりその有効性を示した。新しい方向性を打ち出し、有効性を示すことができたので、学術的な意義は大きいと考えられる。また、細胞生物学などの他の分野の画像も利用しているので、異分野への貢献もできた。

URL: 

Published: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi