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

In this paper we address the challenging problem of domain adaptation inLiDAR semantic segmentation. We consider the setting where we have afully-labeled data set from source domain and a target domain with a fewlabeled and many unlabeled examples. We propose a domain adaption frameworkthat mitigates the issue of domain shift and produces appealing performance onthe target domain. To this end, we develop a GAN-based image-to-imagetranslation engine that has generators with alternating connections, and coupleit with a state-of-the-art LiDAR semantic segmentation network. Our frameworkis hybrid in nature in the sense that our model learning is composed ofself-supervision, semi-supervision and unsupervised learning. Extensiveexperiments on benchmark LiDAR semantic segmentation data sets demonstrate thatour method achieves superior performance in comparison to strong baselines andprior arts.

Domain Adaptation in LiDAR Semantic Segmentation via Alternating Skip Connections and Hybrid Learning