Unsupervised Image-to-Image Translation with Generative Adversarial Networks

Abstract

It's useful to automatically transform an image from its original form to some synthetic form (style, partial contents, etc.), while keeping the original structure or semantics. We define this requirement as the "image-to-image translation" problem, and propose a general approach to achieve it, based on deep convolutional and conditional generative adversarial networks (GANs), which has gained a phenomenal success to learn mapping images from noise input since 2014. In this work, we develop a two step (unsupervised) learning method to translate images between different domains by using unlabeled images without specifying any correspondence between them, so that to avoid the cost of acquiring labeled data. Compared with prior works, we demonstrated the capacity of generality in our model, by which variance of translations can be conduct by a single type of model. Such capability is desirable in applications like bidirectional translation

References in corpus (1)

• Conditional Generative Adversarial Nets

Cited by in corpus (7)

• TensorLayer: A Versatile Library for Efficient Deep Learning Development
• Characterizing Bias in Classifiers using Generative Models
• CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare Records
• AlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networks
• Collision Detection: An Improved Deep Learning Approach Using SENet and ResNext
• Disentanglement for Discriminative Visual Recognition
• MU-GAN: Facial Attribute Editing based on Multi-attention Mechanism