Learning to disentangle and represent factors of variation in data is an important problem in
artificial intelligence. While many advances have been made to learn these representations …

Image-to-image translation (I2I) aims to transfer images from a source domain to a target
domain while preserving the content representations. I2I has drawn increasing attention and …

Recently, image-to-image translation has made significant progress in achieving both multi-
label (ie, translation conditioned on different labels) and multi-style (ie, generation with …

We address the problem of domain generalizable object detection, which aims to learn a
domain-invariant detector from multiple" seen" domains so that it can generalize well to …

Abstract Underwater Image Rendering aims to generate a true-to-life underwater image from
a given clean one, which could be applied to various practical applications such as …

Recent advances of image-to-image translation focus on learning the one-to-many map**
from two aspects: multi-modal translation and multi-domain translation. However, the …

In recent years, Generative Adversarial Networks have become ubiquitous in both research
and public perception, but how GANs convert an unstructured latent code to a high quality …

Cross-domain disentanglement is the problem of learning representations partitioned into
domain-invariant and domain-specific representations, which is a key to successful domain …

We introduce LOGAN, a deep neural network aimed at learning generalpurpose shape
transforms from unpaired domains. The network is trained on two sets of shapes, eg, tables …

We describe a method to train a generative model with latent factors that are (approximately)
independent and localized. This means that perturbing the latent variables affects only local …