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

Adversarial Discriminative Attention for Robust Anomaly Detection #153

Open
yiskw713 opened this issue May 25, 2020 · 0 comments
Open

Adversarial Discriminative Attention for Robust Anomaly Detection #153

yiskw713 opened this issue May 25, 2020 · 0 comments

Comments

@yiskw713
Copy link
Owner

INFO

author

Daiki Kimura, Subhajit Chaudhury, Minori Narita, Asim Munawar, Ryuki Tachibana

affiliation

conference or year

WACV2020

link

pdf

概要

異常検知にCAMを導入した論文.再構成誤差を用いて異常度を算出する際に,全てのピクセルを等しく扱うのではなく,CAMの値を用いて重み付けすることによって異常度を算出する.

Screen Shot 2020-05-25 at 16 22 57

検証

Screen Shot 2020-05-25 at 16 23 29

Comment

  • もう少し複雑なデータセットだとどうなるのか気になった
  • CAMの正規化はどうやっているのだろうか.Discriminator の結果に対するCAMなので,当然(学習していない)画像領域に対してCAMが出るはずだが,正常な画像に対してもCAMが出ている.これは画像ごとの正規化をしているからっぽいけど,これは良い?

date

May 25th, 2020

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