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.
Source: A U-Net Based Discriminator for Generative Adversarial NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Segmentation | 1 | 25.00% |
Medical Image Segmentation | 1 | 25.00% |
Retinal Vessel Segmentation | 1 | 25.00% |
Weakly supervised segmentation | 1 | 25.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |