Conditional image generation is the task of generating new images from a dataset conditional on their class.
( Image credit: PixelCNN++ )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Simultaneously, the generator attempts to synthesize images to fool the discriminator and to maximize the mutual information of fake images from the same class prior.
Ranked #4 on Conditional Image Generation on CIFAR-10 (FID metric)
We do hope that this series will provide you a big overview of the field, so that you will not need to read all the literature by yourself, independent of your background on GANs.
In the first stage, we leverage the inter-class variation of the data distribution for the task of conditional image synthesis by learning the inter-class mapping and synthesizing under-represented class samples from the over-represented ones using unpaired image-to-image translation.
Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled with a Markov chain.
The instability in GAN training has been a long-standing problem despite remarkable research efforts.
Ranked #1 on Conditional Image Generation on CIFAR-100
GLICO is then used to augment the small training set while training a classier on the small sample.
Though recent research has achieved remarkable progress in generating realistic images with generative adversarial networks (GANs), the lack of training stability is still a lingering concern of most GANs, especially on high-resolution inputs and complex datasets.
This way, the hallucinated details are integrated with the style of the original image, in an attempt to further boost the quality of the result and possibly allow for arbitrary output resolutions to be supported.
Ranked #1 on Image Outpainting on Places365-Standard
We propose a new algorithm to incorporate class conditional information into the discriminator of GANs via a multi-class generalization of the commonly used Hinge loss.
Ranked #2 on Conditional Image Generation on CIFAR-100