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

In this paper, we are interested in generating fine-grained cartoon faces forvarious groups. We assume that one of these groups consists of sufficienttraining data while the others only contain few samples. Although the cartoonfaces of these groups share similar style, the appearances in various groupscould still have some specific characteristics, which makes them differ fromeach other. A major challenge of this task is how to transfer knowledge amonggroups and learn group-specific characteristics with only few samples. In orderto solve this problem, we propose a two-stage training process. First, a basictranslation model for the basic group (which consists of sufficient data) istrained. Then, given new samples of other groups, we extend the basic model bycreating group-specific branches for each new group. Group-specific branchesare updated directly to capture specific appearances for each group while theremaining group-shared parameters are updated indirectly to maintain thedistribution of intermediate feature space. In this manner, our approach iscapable to generate high-quality cartoon faces for various groups.

Few-shot Knowledge Transfer for Fine-grained Cartoon Face Generation