Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection

Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection

https://arxiv.org/abs/2107.13118

Nov 4, 2021

Anomaly Detection, Unsupervised Learning, GAN,

ICCV (2021)

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?

5. 関連文献

  1. Dong Gong, Lingqiao Liu, Vuong Le, Budhaditya Saha, Moussa Reda Mansour, Svetha Venkatesh, and Anton van den Hengel. Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In Proceedings of the IEEE International Conference on Computer Vision, pages 1705–1714, 2019. 2,
一覧へ戻る