Prescribed Generative Adversarial Networks

Generative adversarial networks (GANs) are a powerful approach to unsupervised learning. They have achieved state-of-the-art performance in the image domain... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Generation CelebA 128 x 128 PresGAN FID 29.115 # 2
Image Generation CIFAR-10 PresGAN FID 52.202 # 48
Image Generation MNIST PresGAN FID 42.019 # 4
Image Generation Stacked MNIST PresGAN FID 23.965 # 2

Methods used in the Paper


METHOD TYPE
Batch Normalization
Normalization
ReLU
Activation Functions
Leaky ReLU
Activation Functions
DCGAN
Generative Models
PresGAN
Generative Models
Entropy Regularization
Regularization
Convolution
Convolutions
GAN
Generative Models