FA-GAN: Feature-Aware GAN for Text to Image Synthesis
This work addresses a key challenge in text-to-image synthesis for applications like content creation, though it appears incremental as it builds on existing GAN methods.
The paper tackles the problem of generating intact objects and clear textures in text-to-image synthesis by proposing FA-GAN, which integrates a self-supervised discriminator and a feature-aware loss, resulting in a significant improvement in FID score from 28.92 to 24.58 on the MS-COCO dataset.
Text-to-image synthesis aims to generate a photo-realistic image from a given natural language description. Previous works have made significant progress with Generative Adversarial Networks (GANs). Nonetheless, it is still hard to generate intact objects or clear textures (Fig 1). To address this issue, we propose Feature-Aware Generative Adversarial Network (FA-GAN) to synthesize a high-quality image by integrating two techniques: a self-supervised discriminator and a feature-aware loss. First, we design a self-supervised discriminator with an auxiliary decoder so that the discriminator can extract better representation. Secondly, we introduce a feature-aware loss to provide the generator more direct supervision by employing the feature representation from the self-supervised discriminator. Experiments on the MS-COCO dataset show that our proposed method significantly advances the state-of-the-art FID score from 28.92 to 24.58.