@conference {blum:GCPR:2018, title = {X-GAN: Improving Generative Adversarial Networks with ConveX Combinations}, booktitle = {German Conference on Pattern Recognition (GCPR) (Oral)}, year = {2018}, address = {Stuttgart, Germany}, abstract = {Even though recent neural architectures for image generation are capable of producing photo-realistic results, the overall distributions of real and faked images still differ a lot. While the lack of a structured latent representation for GANs often results in mode collapse, VAEs enforce a prior to the latent space that leads to an unnatural representation of the underlying real distribution. We introduce a method that preserves the natural structure of the latent manifold. By utilizing neighboring relations within the set of discrete real samples, we reproduce the full continuous latent manifold. We propose a novel image generation network X-GAN that creates latent input vectors from random convex combinations of adjacent real samples. This way we ensure a structured and natural latent space by not requiring prior assumptions. In our experiments, we show that our model outperforms recent approaches in terms of the missing mode problem while maintaining a high image quality.}, keywords = {deep learning, generative adversarial network, generative model, variational auto-encoder}, author = {Blum, O. and Biagio Brattoli and Bj{\"o}rn Ommer} }