Iterative energy-based projection on a normal data manifold for anomaly localization

Iterative energy-based projection on a normal data manifold for anomaly localization

https://arxiv.org/abs/2002.03734

Aug 3, 2021

Anomaly Detection, Unsupervised Learning, VAE, Anomaly Localization,

ICLR (2020)

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. 議論はあるか?

エネルギー関数の再構成誤差の中身

6. 関連文献

  1. Takashi Matsubara, Ryosuke Tachibana, and Kuniaki Uehara. Anomaly machine component detec- tion by deep generative model with unregularized score. CoRR, abs/1807.05800, 2018.
  2. Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In Yoshua Bengio and Yann LeCun (eds.), 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, 2015.
  3. Thomas Schlegl, Philipp Seeböck, Sebastian M Waldstein, Ursula Schmidt-Erfurth, and Georg Langs. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In International Conference on Information Processing in Medical Imaging, pp. 146– 157. Springer, 2017.
一覧へ戻る