papers AI Learner
The Github is limit! Click to go to the new site.

Harmonizing Maximum Likelihood with GANs for Multimodal Conditional Generation

2019-02-25
Soochan Lee, Junsoo Ha, Gunhee Kim

Abstract

Recent advances in conditional image generation tasks, such as image-to-image translation and image inpainting, are largely accounted to the success of conditional GAN models, which are often optimized by the joint use of the GAN loss with the reconstruction loss. However, we reveal that this training recipe shared by almost all existing methods causes one critical side effect: lack of diversity in output samples. In order to accomplish both training stability and multimodal output generation, we propose novel training schemes with a new set of losses named moment reconstruction losses that simply replace the reconstruction loss. We show that our approach is applicable to any conditional generation tasks by performing thorough experiments on image-to-image translation, super-resolution and image inpainting using Cityscapes and CelebA dataset. Quantitative evaluations also confirm that our methods achieve a great diversity in outputs while retaining or even improving the visual fidelity of generated samples.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1902.09225

PDF

https://arxiv.org/pdf/1902.09225


Similar Posts

Comments