<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Blum, O.</style></author><author><style face="normal" font="default" size="100%">Biagio Brattoli</style></author><author><style face="normal" font="default" size="100%">Björn Ommer</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">X-GAN: Improving Generative Adversarial Networks with ConveX Combinations</style></title><secondary-title><style face="normal" font="default" size="100%">German Conference on Pattern Recognition (GCPR) (Oral)</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">deep learning</style></keyword><keyword><style  face="normal" font="default" size="100%">generative adversarial network</style></keyword><keyword><style  face="normal" font="default" size="100%">generative model</style></keyword><keyword><style  face="normal" font="default" size="100%">variational auto-encoder</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2018</style></year></dates><pub-location><style face="normal" font="default" size="100%">Stuttgart, Germany</style></pub-location><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">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.</style></abstract></record></records></xml>