U-Net GAN

2000년 도입 · 논문 2편에서 사용

In contrast to typical GANs, a U-Net GAN uses a segmentation network as the discriminator. This segmentation network predicts two classes: real and fake. In doing so, the discriminator gives the generator region-specific feedback. This discriminator design also enables a CutMix-based consistency regularization on the two-dimensional output of the U-Net GAN discriminator, which further improves image synthesis quality.

출처: A U-Net Based Discriminator for Generative Adversarial Networks

소개 논문: A U-Net Based Discriminator for Generative Adversarial Networks