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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The point cloud representation of an object can have a large geometricvariation in view of inconsistent data acquisition procedure, which thus leadsto domain discrepancy due to diverse and uncontrollable shape representationcross datasets. To improve discrimination on unseen distribution of point-basedgeometries in a practical and feasible perspective, this paper proposes a newmethod of geometry-aware self-training (GAST) for unsupervised domainadaptation of object point cloud classification. Specifically, this paper aimsto learn a domain-shared representation of semantic categories, via two novelself-supervised geometric learning tasks as feature regularization. On onehand, the representation learning is empowered by a linear mixup of point cloudsamples with their self-generated rotation labels, to capture a globaltopological configuration of local geometries. On the other hand, a diversepoint distribution across datasets can be normalized with a novelcurvature-aware distortion localization. Experiments on the PointDA-10 datasetshow that our GAST method can significantly outperform the state-of-the-artmethods.

Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds