Reverse Variational Autoencoder for Visual Attribute Manipulation and Anomaly Detection

Gauerhof Lydia, Nianlong Gu; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 2114-2123

Abstract


In this paper, we introduce the `Reverse Variational Autoencoder" (Reverse-VAE) which is a generative network. On the one hand, visual attributes can be manipulated and combined while generating images. On the other hand, anomalies, meaning deviations from the data space used for training, can be detected. During training the generator network maps samples from stochastic latent vectors to the data space. Meanwhile the encoder network takes these generated images to reconstruct the latent vector. The generator and discriminator are trained adversarially. The discriminator is trained to distinguish between real and generated data. Overall, our model tries to match the joint latent/data-space distribution of the generator and the latent/data-space joint distribution of the encoder by minimizing their Kullback-Leibler divergence. Desired visual attributes of CelebA images are successfully manipulated. The performance of anomaly detection is competitive with state-of-the-art on MNIST and KDD 99 data set.

Related Material


[pdf] [video]
[bibtex]
@InProceedings{Lydia_2020_WACV,
author = {Lydia, Gauerhof and Gu, Nianlong},
title = {Reverse Variational Autoencoder for Visual Attribute Manipulation and Anomaly Detection},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2020}
}