English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Among the major remaining challenges for generative adversarial networks(GANs) is the capacity to synthesize globally and locally coherent images withobject shapes and textures indistinguishable from real images. To target thisissue we propose an alternative U-Net based discriminator architecture,borrowing the insights from the segmentation literature. The proposed U-Netbased architecture allows to provide detailed per-pixel feedback to thegenerator while maintaining the global coherence of synthesized images, byproviding the global image feedback as well. Empowered by the per-pixelresponse of the discriminator, we further propose a per-pixel consistencyregularization technique based on the CutMix data augmentation, encouraging theU-Net discriminator to focus more on semantic and structural changes betweenreal and fake images. This improves the U-Net discriminator training, furtherenhancing the quality of generated samples. The novel discriminator improvesover the state of the art in terms of the standard distribution and imagequality metrics, enabling the generator to synthesize images with varyingstructure, appearance and levels of detail, maintaining global and localrealism. Compared to the BigGAN baseline, we achieve an average improvement of2.7 FID points across FFHQ, CelebA, and the newly introduced COCO-Animalsdataset. The code is available at https://github.com/boschresearch/unetgan.

A U-Net Based Discriminator for Generative Adversarial Networks