JeongJiHeon / Torch

Octave Convolution

• [OctConv][https://arxiv.org/abs/1904.05049]

data = STL10

data = CIFAR10

It doesn't look good in a small model.

Generative Model

Generative Adversarial Network (GAN)

• [GAN][https://arxiv.org/pdf/1406.2661.pdf]
• [DCGAN][https://arxiv.org/pdf/1511.06434.pdf]
• [cGAN][https://arxiv.org/pdf/1411.1784.pdf]
• [pix2pix][https://arxiv.org/pdf/1611.07004.pdf]
• [CycleGAN][https://arxiv.org/pdf/1703.10593.pdf]
• [WGAN][https://arxiv.org/pdf/1701.07875.pdf]
• [WGAN-GP][https://arxiv.org/pdf/1704.00028]

WGAN-GP

CycleGAN

pix2pix

Conditional GAN

DCGAN

AutoEncoder (AE)

• [VAE][https://arxiv.org/pdf/1312.6114.pdf]

VAE