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 domain adaptation (UDA) addresses the problem of distributionshift between the unlabelled target domain and labelled source domain. Whilethe single target domain adaptation (STDA) is well studied in the literaturefor both 2D and 3D vision tasks, multi-target domain adaptation (MTDA) isbarely explored for 3D data despite its wide real-world applications such asautonomous driving systems for various geographical and climatic conditions. Weestablish an MTDA baseline for 3D point cloud data by proposing to mix thefeature representations from all domains together to achieve better domainadaptation performance by an ensemble average, which we call Mixup EnsembleAverage or MEnsA. With the mixed representation, we use a domain classifier toimprove at distinguishing the feature representations of source domain fromthose of target domains in a shared latent space. In empirical validations onthe challenging PointDA-10 dataset, we showcase a clear benefit of our simplemethod over previous unsupervised STDA and MTDA methods by large margins (up to17.10% and 4.76% on averaged over all domain shifts).

MEnsA: Mix-up Ensemble Average for Unsupervised Multi Target Domain Adaptation on 3D Point Clouds