A U-Net Based Discriminator for Generative Adversarial Networks

28 Feb 2020 Edgar Schönfeld Bernt Schiele Anna Khoreva

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... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Generation CelebA 128x128 U-Net GAN FID 2.95 # 1
Inception score 3.43 # 1
Image Generation CelebA-HQ 128x128 U-Net GAN FID 2.03 # 1
Inception score 3.33 # 1
Conditional Image Generation COCO-Animals BigGAN FID 16.37 # 2
IS 11.77 # 2
Conditional Image Generation COCO-Animals U-Net GAN FID 13.73 # 1
IS 12.29 # 1
Image Generation FFHQ 256 x 256 BigGAN FID 11.48 # 2
IS 3.97 # 2
Image Generation FFHQ 256 x 256 U-Net GAN FID 7.48 # 1
IS 4.46 # 1

Methods used in the Paper