Autoregressive Generative Adversarial Networks

Yasin Yazici, Kim-Hui Yap, Stefan Winkler

Feb 07, 2018 (modified: Feb 15, 2018) ICLR 2018 Workshop Submission readers: everyone Show Bibtex
  • Abstract: Generative Adversarial Networks (GANs) learn a generative model by playing an adversarial game between a generator and an auxiliary discriminator, which classifies data samples vs.\ generated ones. However, it does not explicitly model feature co-occurrences in samples. In this paper, we propose a novel Autoregressive Generative Adversarial Network (ARGAN), that models the latent distribution of data using an autoregressive model, rather than relying on binary classification of samples into data/generated categories. In this way, feature co-occurrences in samples can be more efficiently captured. Our model was evaluated on two widely used datasets: CIFAR-10 and STL-10. Its performance is competitive with respect to other GAN models both quantitatively and qualitatively.
  • Keywords: Generative Adversarial Networks, Auto-regressive Modeling