Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection

Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection

https://arxiv.org/abs/2110.02855

Oct 28, 2021

Anomaly Detection, Flow,

WACV (2022)

1. どんなもの?

2. 先行研究と比べてどこがすごい?

3. 技術や手法の”キモ”はどこ?

変数定義

学習

推論(異常度の算出)

4. どうやって有効だと検証した?

6. 関連文献

  1. Laurent Dinh, Jascha Sohl-Dickstein, and Samy Bengio. Density estimation using real nvp. ICLR 2017, 2016.
  2. Marco Rudolph, Bastian Wandt, and Bodo Rosenhahn. Same same but differnet: Semi-supervised defect detection with normalizing flows. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1907–1916, 2021.
一覧へ戻る