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

Domain Adaptation is a technique to address the lack of massive amounts oflabeled data in unseen environments. Unsupervised domain adaptation is proposedto adapt a model to new modalities using solely labeled source data andunlabeled target domain data. Though many image-spaces domain adaptationmethods have been proposed to capture pixel-level domain-shift, such techniquesmay fail to maintain high-level semantic information for the segmentation task.For the case of biomedical images, fine details such as blood vessels can belost during the image transformation operations between domains. In this work,we propose a model that adapts between domains using cycle-consistent losswhile maintaining edge details of the original images by enforcing anedge-based loss during the adaptation process. We demonstrate the effectivenessof our algorithm by comparing it to other approaches on two eye fundus vesselssegmentation datasets. We achieve 1.1 to 9.2 increment in DICE score comparedto the SOTA and ~5.2 increments compared to a vanilla CycleGAN implementation.

Edge-preserving Domain Adaptation for semantic segmentation of Medical Images