U-Net GAN

U-Net Generative Adversarial Network

Computer VisionIntroduced 20002 papers

Description

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.

Papers Using This Method

OCTAve: 2D en face Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning with Locality Augmentation2022-07-25 A U-Net Based Discriminator for Generative Adversarial Networks2020-06-01