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

Learning models on one labeled dataset that generalize well on another domainis a difficult task, as several shifts might happen between the data domains.This is notably the case for lidar data, for which models can exhibit largeperformance discrepancies due for instance to different lidar patterns orchanges in acquisition conditions. This paper addresses the correspondingUnsupervised Domain Adaptation (UDA) task for semantic segmentation. Tomitigate this problem, we introduce an unsupervised auxiliary task of learningan implicit underlying surface representation simultaneously on source andtarget data. As both domains share the same latent representation, the model isforced to accommodate discrepancies between the two sources of data. This novelstrategy differs from classical minimization of statistical divergences orlidar-specific domain adaptation techniques. Our experiments demonstrate thatour method achieves a better performance than the current state of the art,both in real-to-real and synthetic-to-real scenarios.

SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation