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

LaSO: Label-Set Operations networks for multi-label few-shot learning #1

Open
ysasano opened this issue Mar 4, 2019 · 0 comments
Open

Comments

@ysasano
Copy link
Owner

ysasano commented Mar 4, 2019

一言でいうと

マルチラベルのfew shot learningタスクにおいて集合演算の結果を最適化する手法の提案。2枚の画像をInceptionV3で特徴抽出し、そこからそれぞれのラベル / ラベルの和集合 / 積集合 / 差集合を推論する。集合演算には「逆順にしても同じ結果になる」などの拘束条件があるので再構築誤差も利用する。

combined_model

論文リンク

https://arxiv.org/abs/1902.09811

著者/所属機関

Amit Alfassy, Leonid Karlinsky, Amit Aides, Joseph Shtok, Sivan Harary, Rogerio Feris, Raja Giryes, Alex M. Bronstein

  • IBM Research AI
  • School of Electrical Engineering, Tel-Aviv University
  • Department of Computer Science, Technion

投稿日付(yyyy/MM/dd)

2019/2/29

概要

新規性・差分

手法

結果

コメント

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