Find the slides at slides.com/eiffl/ano
Disclaimer: This is NOT an exhaustive review, there are many hundreds of anomaly detection papers out there
Also, remember our session last year led by Ben Nachman
Because a number of samples are drawn from the latent variable distribution, this allows the reconstruction probability to take into account the variability of the latent variable space, which is one of the main distinctions between the proposed method and the autoencoder based anomaly detection.
A Lipschitz-constrained anomaly discriminator framework, Tong et al. 2019
This loss after optimization will be the anomaly score
Work led by the amazing Kate Storey-Fisher (NYU) @kstoreyf
Real HSC images
GAN generated images
Low and high anomaly scores
I recommend checking out this great set of slides:
http://www.gatsby.ucl.ac.uk/~balaji/mluq-talk-balaji.pdf