IAN: Combining Generative Adversarial Networks for Imaginative Face Generation

by   Abdullah Hamdi, et al.

Generative Adversarial Networks (GANs) have gained momentum for their ability to model image distributions. They learn to emulate the training set and that enables sampling from that domain and using the knowledge learned for useful applications. Several methods proposed enhancing GANs, including regularizing the loss with some feature matching. We seek to push GANs beyond the data in the training and try to explore unseen territory in the image manifold. We first propose a new regularizer for GAN based on K-nearest neighbor (K-NN) selective feature matching to a target set Y in high-level feature space, during the adversarial training of GAN on the base set X, and we call this novel model K-GAN. We show that minimizing the added term follows from cross-entropy minimization between the distributions of GAN and the set Y. Then, We introduce a cascaded framework for GANs that try to address the task of imagining a new distribution that combines the base set X and target set Y by cascading sampling GANs with translation GANs, and we dub the cascade of such GANs as the Imaginative Adversarial Network (IAN). We conduct an objective and subjective evaluation for different IAN setups in the addressed task and show some useful applications for these IANs, like manifold traversing and creative face generation for characters' design in movies or video games.


page 6

page 8

page 15

page 16

page 17

page 18

page 20

page 22


McGan: Mean and Covariance Feature Matching GAN

We introduce new families of Integral Probability Metrics (IPM) for trai...

On the Performance of Generative Adversarial Network (GAN) Variants: A Clinical Data Study

Generative Adversarial Network (GAN) is a useful type of Neural Networks...

Adversarial Training For Sketch Retrieval

Generative Adversarial Networks (GAN) are able to learn excellent repres...

Evaluating a GAN for enhancing camera simulation for robotics

Given the versatility of generative adversarial networks (GANs), we seek...

Generative Adversarial Network Rooms in Generative Graph Grammar Dungeons for The Legend of Zelda

Generative Adversarial Networks (GANs) have demonstrated their ability t...

Adversarial Training of Word2Vec for Basket Completion

In recent years, the Word2Vec model trained with the Negative Sampling l...

MetroGAN: Simulating Urban Morphology with Generative Adversarial Network

Simulating urban morphology with location attributes is a challenging ta...

Please sign up or login with your details

Forgot password? Click here to reset