Abstract
Image generation with explicit condition or label generally works better than unconditional methods. In modern GAN frameworks, both generator and discriminator are formulated to model the conditional distribution of images given with labels. In this paper, we provide an alternative formulation of GAN which models the joint distribution of images and labels. There are two advantages in this joint formulation over conditional approaches. The first advantage is that the joint formulation is more robust to label noises if it's properly modeled. This alleviates the burden of making noise-free labels and allows the use of weakly-supervised labels in image generation. The second is that we can use any kinds of weak labels or image features that have correlations with the original image data to enhance unconditional image generation. We will show the effectiveness of our joint formulation on CIFAR10, CIFAR100, and STL dataset with the state-of-the-art GAN architecture.
Highlights
Due to the success of Generative Adversarial Network (GAN) for modeling distributions of real world data, it has been widely used for image generation
We propose an alternative formulation of GAN which models the joint distribution of images and labels
We propose a novel GAN formulation that models the joint distribution of images and labels, and show that this joint formulation increases the robustness on noisy or weak labels
Summary
Due to the success of Generative Adversarial Network (GAN) for modeling distributions of real world data, it has been widely used for image generation. In modern GAN frameworks, both generator and discriminator are formulated to model the conditional distribution of images given with labels. We propose an alternative formulation of GAN which models the joint distribution of images and labels.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
