LOGAN-B: Bidirectional Latent Optimized Generative Adversarial Networks

The inductive bias of generative adversarial networks is a powerful tool for learning distributions of data. However, these models are difficult to train and very susceptible to mode collapse, capturing only a few modes of the data distribution. In this work, we introduce bidirectional latent optimized generative adversarial networks as a framework for training generative adversarial networks to mitigate this problem by encouraging the generator to maintain a mapping to the data distribution.

[Report]

Synthetic Data

GAN: Jupyter Notebook

BiGAN: Jupyter Notebook

LOGAN-B: Jupyter Notebook

MNIST

DCGAN: Jupyter Notebook

BiGAN: Jupyter Notebook

LOGAN-B: Jupyter Notebook

CIFAR10

DCGAN: Jupyter Notebook

BiGAN: Jupyter Notebook

LOGAN-B: Jupyter Notebook

Bootstrap: Jupyter Notebook

Interpolation: Jupyter Notebook

_{^{Course Project for CS670 @ UMass Amherst}}