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/

Zendy Plus

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

Zendy Tools

Zendy Open

In this paper, we introduce DuelGAN, a generative adversarial network (GAN)solution to improve the stability of the generated samples and to mitigate modecollapse. Built upon the Vanilla GAN's two-player game between thediscriminator $D_1$ and the generator $G$, we introduce a peer discriminator$D_2$ to the min-max game. Similar to previous work using two discriminators,the first role of both $D_1$, $D_2$ is to distinguish between generated samplesand real ones, while the generator tries to generate high-quality samples whichare able to fool both discriminators. Different from existing methods, weintroduce another game between $D_1$ and $D_2$ to discourage their agreementand therefore increase the level of diversity of the generated samples. Thisproperty alleviates the issue of early mode collapse by preventing $D_1$ and$D_2$ from converging too fast. We provide theoretical analysis for theequilibrium of the min-max game formed among $G, D_1, D_2$. We offerconvergence behavior of DuelGAN as well as stability of the min-max game. It'sworth mentioning that DuelGAN operates in the unsupervised setting, and theduel between $D_1$ and $D_2$ does not need any label supervision. Experimentsresults on a synthetic dataset and on real-world image datasets (MNIST, FashionMNIST, CIFAR-10, STL-10, CelebA, VGG, and FFHQ) demonstrate that DuelGANoutperforms competitive baseline work in generating diverse and high-qualitysamples, while only introduces negligible computation cost.

DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training