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

Recently, unsupervised image-to-image translation methods based oncontrastive learning have achieved state-of-the-art results in many tasks.However, in the previous works, the negatives are sampled from the input imageitself, which inspires us to design a data augmentation method to improve thequality of the selected negatives. Moreover, the previous methods only preservethe content consistency via patch-wise contrastive learning in the embeddingspace, which ignores the domain consistency between the generated images andthe real images of the target domain. In this paper, we propose a novelunsupervised image-to-image translation framework based on multi-croppingcontrastive learning and domain consistency, called MCDUT. Specifically, weobtain the multi-cropping views via the center-cropping and the random-croppingwith the aim of further generating the high-quality negative examples. Toconstrain the embeddings in the deep feature space, we formulate a new domainconsistency loss, which encourages the generated images to be close to the realimages in the embedding space of the same domain. Furthermore, we present adual coordinate attention network by embedding positional information into thechannel, which called DCA. We employ the DCA network in the design ofgenerator, which makes the generator capture the horizontal and vertical globalinformation of dependency. In many image-to-image translation tasks, our methodachieves state-of-the-art results, and the advantages of our method have beenproven through extensive comparison experiments and ablation research.

Multi-cropping Contrastive Learning and Domain Consistency for Unsupervised Image-to-Image Translation