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-to-image (I2I) translation learns cross-domain imagemapping that transfers input from the source domain to output in the targetdomain while preserving its semantics. One challenge is that different semanticstatistics in source and target domains result in content discrepancy known assemantic distortion. To address this problem, a novel I2I method that maintainssemantic consistency in translation is proposed and named SemST in this work.SemST reduces semantic distortion by employing contrastive learning andaligning the structural and textural properties of input and output bymaximizing their mutual information. Furthermore, a multi-scale approach isintroduced to enhance translation performance, thereby enabling theapplicability of SemST to domain adaptation in high-resolution images.Experiments show that SemST effectively mitigates semantic distortion andachieves state-of-the-art performance. Also, the application of SemST to domainadaptation (DA) is explored. It is demonstrated by preliminary experiments thatSemST can be utilized as a beneficial pre-training for the semanticsegmentation task.

SemST: Semantically Consistent Multi-Scale Image Translation via Structure-Texture Alignment