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

Unsupervised image translation, which aims in translating two independentsets of images, is challenging in discovering the correct correspondenceswithout paired data. Existing works build upon Generative Adversarial Network(GAN) such that the distribution of the translated images are indistinguishablefrom the distribution of the target set. However, such set-level constraintscannot learn the instance-level correspondences (e.g. aligned semantic parts inobject configuration task). This limitation often results in false positives(e.g. geometric or semantic artifacts), and further leads to mode collapseproblem. To address the above issues, we propose a novel framework forinstance-level image translation by Deep Attention GAN (DA-GAN). Such a designenables DA-GAN to decompose the task of translating samples from two sets intotranslating instances in a highly-structured latent space. Specifically, wejointly learn a deep attention encoder, and the instancelevel correspondencescould be consequently discovered through attending on the learned instancepairs. Therefore, the constraints could be exploited on both set-level andinstance-level. Comparisons against several state-ofthe- arts demonstrate thesuperiority of our approach, and the broad application capability, e.g, posemorphing, data augmentation, etc., pushes the margin of domain translationproblem.

DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)