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.

Sign up for GitHub

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

Jump to bottom

Certifiably Adversarially Robust Detection of Out-of-Distribution Data #40

Open

nocotan opened this issue Feb 25, 2021 · 0 comments

Assignees

Labels

out-of-distribution detection

Member

nocotan commented Feb 25, 2021

一言でいうと

最悪ケース保証付きOOD detectionの手法であるGOODを提案

論文リンク

https://papers.nips.cc/paper/2020/file/b90c46963248e6d7aab1e0f429743ca0-Paper.pdf

著者/所属機関

Julian Bitterwolf et al.
(University of Tübingen)

投稿日付(yyyy/MM/dd)

2020/12

概要

DNNsはOODサンプルに対するoverconfident問題を持つ．
論文では，OOD detectionの最悪ケースを保証することを考える．

新規性・差分

最悪ケース保証付きOOD detectionの手法であるGOODを提案

手法

結果

コメント

nocotan added the out-of-distribution detection label

nocotan self-assigned this

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment