A U-Net Based Discriminator for Generative Adversarial Networks

Understand

Among the major remaining challenges for generative adversarial networks (GANs) is the capacity to synthesize globally and locally coherent images with object shapes and textures indistinguishable from real images.

• To target this issue we propose an alternative U-Net based discriminator architecture, borrowing the insights from the segmentation literature.
• The proposed U-Net based architecture allows to provide detailed per-pixel feedback to the generator while maintaining the global coherence of synthesized images, by providing the global image feedback as well.
• Empowered by the per-pixel response of the discriminator, we further propose a per-pixel consistency regularization technique based on the CutMix data augmentation, encouraging the U-Net discriminator to focus more on semantic and structural changes between real and fake images.