ZIYU-DEEP / adVAE

Implementation of 'Self-Adversarial Variational Autoencoder with Gaussian Anomaly Prior Distribution for Anomaly Detection'

adVAE (Self-Adversarial Variational Autoencoder)

Implementation of 'Self-Adversarial Variational Autoencoder with Gaussian Anomaly Prior Distribution for Anomaly Detection' (adVAE) [Related repository].

Architecture

Simplified adVAE architecture.

Graph in TensorBoard

Graph of adVAE.

Results

Restoration result by adVAE.

Box plot and histogram of restoration loss in test procedure.

Normal latent space, and transformed latent space (regared as abnormal).

Environment

• Python 3.7.4
• Tensorflow 1.14.0
• Numpy 1.17.1
• Matplotlib 3.1.1
• Scikit Learn (sklearn) 0.21.3

Reference

[1] Xuhong Wang, et al. (2019). Self-adversarial Variational Autoencoder with Gaussian Anomaly Prior Distribution for Anomaly Detection.. arXiv preprint arXiv:1903.00904.