Open AccessProceedings Article
Mode regularized generative adversarial networks
TLDR
In this paper, the authors introduce several ways of regularizing the objective, which can dramatically stabilize the training of GAN models and also show that their regularizers can help the fair distribution of probability mass across the modes of the data generating distribution, during the early phases of training.Abstract:
Although Generative Adversarial Networks achieve state-of-the-art results on a variety of generative tasks, they are regarded as highly unstable and prone to miss modes. We argue that these bad behaviors of GANs are due to the very particular functional shape of the trained discriminators in high dimensional spaces, which can easily make training stuck or push probability mass in the wrong direction, towards that of higher concentration than that of the data generating distribution. We introduce several ways of regularizing the objective, which can dramatically stabilize the training of GAN models. We also show that our regularizers can help the fair distribution of probability mass across the modes of the data generating distribution, during the early phases of training and thus providing a unified solution to the missing modes problem.read more
Citations
More filters
Proceedings ArticleDOI
StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
Han Zhang,Tao Xu,Hongsheng Li +2 more
TL;DR: This paper proposes Stacked Generative Adversarial Networks (StackGAN) to generate 256 photo-realistic images conditioned on text descriptions and introduces a novel Conditioning Augmentation technique that encourages smoothness in the latent conditioning manifold.
Posted Content
Self-Attention Generative Adversarial Networks
TL;DR: Self-Attention Generative Adversarial Network (SAGAN) as mentioned in this paper uses attention-driven, long-range dependency modeling for image generation tasks and achieves state-of-the-art results.
Posted Content
Conditional Adversarial Domain Adaptation
TL;DR: Conditional adversarial domain adaptation is presented, a principled framework that conditions the adversarial adaptation models on discriminative information conveyed in the classifier predictions to guarantee the transferability.
Journal ArticleDOI
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
Han Zhang,Tao Xu,Hongsheng Li,Shaoting Zhang,Xiaogang Wang,Xiaolei Huang,Dimitris N. Metaxas +6 more
TL;DR: Zhang et al. as discussed by the authors proposed a two-stage generative adversarial network architecture, StackGAN-v1, which sketches the primitive shape and colors of a scene based on a given text description, yielding low-resolution images.
Posted Content
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
Han Zhang,Tao Xu,Hongsheng Li,Shaoting Zhang,Xiaogang Wang,Xiaolei Huang,Dimitris N. Metaxas +6 more
TL;DR: Extensive experiments demonstrate that the proposed stacked generative adversarial networks significantly outperform other state-of-the-art methods in generating photo-realistic images.