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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Generating photo-realistic images from a text description is a challengingproblem in computer vision. Previous works have shown promising performance togenerate synthetic images conditional on text by Generative AdversarialNetworks (GANs). In this paper, we focus on the category-consistent andrelativistic diverse constraints to optimize the diversity of synthetic images.Based on those constraints, a category-consistent and relativistic diverseconditional GAN (CRD-CGAN) is proposed to synthesize $K$ photo-realistic imagessimultaneously. We use the attention loss and diversity loss to improve thesensitivity of the GAN to word attention and noises. Then, we employ therelativistic conditional loss to estimate the probability of relatively real orfake for synthetic images, which can improve the performance of basicconditional loss. Finally, we introduce a category-consistent loss to alleviatethe over-category issues between K synthetic images. We evaluate our approachusing the Birds-200-2011, Oxford-102 flower and MSCOCO 2014 datasets, and theextensive experiments demonstrate superiority of the proposed method incomparison with state-of-the-art methods in terms of photorealistic anddiversity of the generated synthetic images.

CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-to-Image Generation