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

ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network #28

Open
ryoherisson opened this issue Jun 3, 2021 · 0 comments

Comments

@ryoherisson
Copy link
Contributor

一言でいうと

表現力のボトルネックを調べ,ボトルネックを軽減するための設計原理を提案.

論文リンク

著者/所属機関

Dongyoon HanSangdoo YunByeongho HeoYoungJoon Yoo
(Clova AI Research, NAVER Corp)

投稿日付(yyyy/MM/dd)

2020/07/02

概要

ある層の表現力は,先行する層のRankによって制限される.これを防ぐために,Rankを増やす手法を提案.

新規性・差分

  • Representation Bottleneckについて調査
  • ImageNetに対してSOTA

手法

結果

コメント

モデル圧縮の分野ではない.

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