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 models have proven to be an outstanding tool for representinghigh-dimensional probability distributions and generating realistic-lookingimages. An essential characteristic of generative models is their ability toproduce multi-modal outputs. However, while training, they are oftensusceptible to mode collapse, that is models are limited in mapping input noiseto only a few modes of the true data distribution. In this work, we drawinspiration from Determinantal Point Process (DPP) to propose an unsupervisedpenalty loss that alleviates mode collapse while producing higher qualitysamples. DPP is an elegant probabilistic measure used to model negativecorrelations within a subset and hence quantify its diversity. We use DPPkernel to model the diversity in real data as well as in synthetic data. Then,we devise an objective term that encourages generators to synthesize data withsimilar diversity to real data. In contrast to previous state-of-the-artgenerative models that tend to use additional trainable parameters or complextraining paradigms, our method does not change the original training scheme.Embedded in an adversarial training and variational autoencoder, our GenerativeDPP approach shows a consistent resistance to mode-collapse on a wide varietyof synthetic data and natural image datasets including MNIST, CIFAR10, andCelebA, while outperforming state-of-the-art methods for data-efficiency,generation quality, and convergence-time whereas being 5.8x faster than itsclosest competitor.

GDPP: Learning Diverse Generations Using Determinantal Point Process