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

In computer vision, one is often confronted with problems of domain shifts,which occur when one applies a classifier trained on a source dataset to targetdata sharing similar characteristics (e.g. same classes), but also differentlatent data structures (e.g. different acquisition conditions). In such asituation, the model will perform poorly on the new data, since the classifieris specialized to recognize visual cues specific to the source domain. In thiswork we explore a solution, named DeepJDOT, to tackle this problem: through ameasure of discrepancy on joint deep representations/labels based on optimaltransport, we not only learn new data representations aligned between thesource and target domain, but also simultaneously preserve the discriminativeinformation used by the classifier. We applied DeepJDOT to a series of visualrecognition tasks, where it compares favorably against state-of-the-art deepdomain adaptation methods.

DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation