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

OOD-MAML: Meta-Learning for Few-Shot Out-of-Distribution Detection and Classification #39

Open
nocotan opened this issue Feb 25, 2021 · 0 comments

Comments

@nocotan
Copy link
Member

nocotan commented Feb 25, 2021

一言でいうと

OOD detectionのためのMAMLに基づくfew-shot learning手法を提案.

論文リンク

https://papers.nips.cc/paper/2020/file/28e209b61a52482a0ae1cb9f5959c792-Paper.pdf

著者/所属機関

Taewon Jeong and Heeyoung Kim
(Department of Industrial and Systems Engineering, KAIST)

投稿日付(yyyy/MM/dd)

2020/12

概要

OOD detectionのためのfew-shot learning手法を提案.
これを達成するために,論文ではin-distributionサンプルに類似したOODサンプルを人工的に生成する.
提案手法はmodel-agnostic meta-learning (MAML)に基づいており,モデルの初期化だけでなく,タスクを通して初期擬似サンプルも学習する.

Screen Shot 2021-02-26 at 3 02 26

新規性・差分

  • OOD detectionのためのMAMLに基づくfew-shot learning手法を提案.

手法

Screen Shot 2021-02-26 at 3 07 08

結果

Screen Shot 2021-02-26 at 3 02 36

Screen Shot 2021-02-26 at 3 02 42

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