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/

Zendy Plus

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

Zendy Tools

Zendy Open

Unsupervised image transfer enables intra- and inter-modality imagetranslation in applications where a large amount of paired training data is notabundant. To ensure a structure-preserving mapping from the input to the targetdomain, existing methods for unpaired image transfer are commonly based oncycle-consistency, causing additional computational resources and instabilitydue to the learning of an inverse mapping. This paper presents a novel methodfor uni-directional domain mapping that does not rely on any paired trainingdata. A proper transfer is achieved by using a GAN architecture and a novelgenerator loss based on patch invariance. To be more specific, the generatoroutputs are evaluated and compared at different scales, also leading to anincreased focus on high-frequency details as well as an implicit dataaugmentation. This novel patch loss also offers the possibility to accuratelypredict aleatoric uncertainty by modeling an input-dependent scale map for thepatch residuals. The proposed method is comprehensively evaluated on threewell-established medical databases. As compared to four state-of-the-artmethods, we observe significantly higher accuracy on these datasets, indicatinggreat potential of the proposed method for unpaired image transfer withuncertainty taken into account. Implementation of the proposed framework isreleased here:\url{https://github.com/anger-man/unsupervised-image-transfer-and-uq}.

Unsupervised Joint Image Transfer and Uncertainty Quantification Using Patch Invariant Networks