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

Generative Adversarial Networks (GANs) have shown compelling results invarious tasks and applications in recent years. However, mode collapse remainsa critical problem in GANs. In this paper, we propose a novel training pipelineto address the mode collapse issue of GANs. Different from existing methods, wepropose to generalize the discriminator as feature embedding and maximize theentropy of distributions in the embedding space learned by the discriminator.Specifically, two regularization terms, i.e., Deep Local Linear Embedding(DLLE) and Deep Isometric feature Mapping (DIsoMap), are designed to encouragethe discriminator to learn the structural information embedded in the data,such that the embedding space learned by the discriminator can be well-formed.Based on the well-learned embedding space supported by the discriminator, anon-parametric entropy estimator is designed to efficiently maximize theentropy of embedding vectors, playing as an approximation of maximizing theentropy of the generated distribution. By improving the discriminator andmaximizing the distance of the most similar samples in the embedding space, ourpipeline effectively reduces the mode collapse without sacrificing the qualityof generated samples. Extensive experimental results show the effectiveness ofour method, which outperforms the GAN baseline, MaF-GAN on CelebA (9.13 vs.12.43 in FID) and surpasses the recent state-of-the-art energy-based model onthe ANIME-FACE dataset (2.80 vs. 2.26 in Inception score). The code isavailable at https://github.com/HaozheLiu-ST/MEE

Combating Mode Collapse in GANs via Manifold Entropy Estimation