Semi-supervised FusedGAN for Conditional Image Generation

TL;DR

FusedGAN is a novel deep network that enables controllable, high-fidelity, and diverse conditional image synthesis by fusing unconditional and conditional generators within a single-stage, disentangled framework.

Contribution

The paper introduces FusedGAN, a single-stage model that fuses unconditional and conditional generators, allowing effective use of unlabeled images and improved controllability in image synthesis.

Findings

FusedGAN achieves high fidelity and diversity in generated images.

The model effectively leverages unlabeled data for training.

Demonstrated success in text-to-image and attribute-to-face generation tasks.

Abstract

We present FusedGAN, a deep network for conditional image synthesis with controllable sampling of diverse images. Fidelity, diversity and controllable sampling are the main quality measures of a good image generation model. Most existing models are insufficient in all three aspects. The FusedGAN can perform controllable sampling of diverse images with very high fidelity. We argue that controllability can be achieved by disentangling the generation process into various stages. In contrast to stacked GANs, where multiple stages of GANs are trained separately with full supervision of labeled intermediate images, the FusedGAN has a single stage pipeline with a built-in stacking of GANs. Unlike existing methods, which requires full supervision with paired conditions and images, the FusedGAN can effectively leverage more abundant images without corresponding conditions in training, to produce more diverse samples with high fidelity. We achieve this by fusing two generators: one for unconditional image generation, and the other for conditional image generation, where the two partly share a common latent space thereby disentangling the generation. We demonstrate the efficacy of the FusedGAN in fine grained image generation tasks such as text-to-image, and attribute-to-face generation.