Iterative Image Inpainting with Structural Similarity Mask for Anomaly Detection

Iterative Image Inpainting with Structural Similarity Mask for Anomaly Detection

https://openreview.net/forum?id=b4ach0lGuYO

Aug 5, 2021

Anomaly Detection, Unsupervised Learning, Structural Similarit, GAN,

ICLR (2021)

1. どんなもの?

オートエンコーダで再構成して異常と判断された領域をマスキングして再構成、ということを繰り返すことで再構成品質を向上させた

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?

5. 議論はあるか?

6. 関連文献

  1. Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A Efros. Image-to-image translation with conditional adversarial networks. In Proceedings ofthe IEEE conference on computer vision and pattern recognition, pp. 1125–1134, 2017.
  2. Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, and Thomas S Huang. Generative image inpainting with contextual attention. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5505–5514, 2018.
  3. Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, and Thomas S Huang. Free-form image inpainting with gated convolution. In Proceedings ofthe IEEE International Conference on Computer Vision, pp. 4471–4480, 2019
一覧へ戻る