Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution #1179

Open
icoxfog417 opened this issue Apr 17, 2019 · 1 comment

Comments

@icoxfog417
Copy link
Member

一言でいうと

CNNで出力される特徴マップを、低周波(解像度が荒い)特徴と高周波(解像度が高い)特徴にわける手法の提案。これにより特徴マップの冗長性を無くし、精度面+演算速度面でメリットが出るとしている。CNNのフィルタを同周波(高=>高・低=>低)・異周波交換(高=>低・低=>高)の4つに分割し実装している

image

論文リンク

https://export.arxiv.org/abs/1904.05049

著者/所属機関

Yunpeng Chen, Haoqi Fang, Bing Xu, Zhicheng Yan, Yannis Kalantidis, Marcus Rohrbach, Shuicheng Yan, Jiashi Feng

  • Facebook AI
  • National University of Singapore
  • Qihoo 360 AI Institute

投稿日付(yyyy/MM/dd)

2019/4/10

概要

新規性・差分

手法

結果

コメント

@icoxfog417
Copy link
Member Author

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant