Student's t-Generative Adversarial Networks
arXiv:1811.02132
Abstract
Generative Adversarial Networks (GANs) have a great performance in image generation, but they need a large scale of data to train the entire framework, and often result in nonsensical results. We propose a new method referring to conditional GAN, which equipments the latent noise with mixture of Student's t-distribution with attention mechanism in addition to class information. Student's t-distribution has long tails that can provide more diversity to the latent noise. Meanwhile, the discriminator in our model implements two tasks simultaneously, judging whether the images come from the true data distribution, and identifying the class of each generated images. The parameters of the mixture model can be learned along with those of GANs. Moreover, we mathematically prove that any multivariate Student's t-distribution can be obtained by a linear transformation of a normal multivariate Student's t-distribution. Experiments comparing the proposed method with typical GAN, DeliGAN and DCGAN indicate that, our method has a great performance on generating diverse and legible objects with limited data.
References in corpus (14)
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
- Improved Techniques for Training GANs
- NIPS 2016 Tutorial: Generative Adversarial Networks
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- Recurrent Models of Visual Attention
- Semi-Supervised Learning with Generative Adversarial Networks
- AdaGAN: Boosting Generative Models
- Dual Discriminator Generative Adversarial Nets
- CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training
- DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data