One-class-novelty-detection-using-variational-autoencoders-with-dual-matching
The goal of this project is to use a new architecture of autoencoder for Novlety detection task
This work is based on GPND ("https://github.com/podgorskiy/GPND")
The main contribution from my side is I have changed the architecture from autoencoder with two discriminator present in the paper to Variational Autoencoder with dual matching.
This architecture is already presented in this paper "https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-020-3401-5" but they have used it for dimentionality detection while we are using for image reconstruction.
Running the code is same as GPND please follow insturctions from that the link