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

Since the preparation of labeled data for training semantic segmentationnetworks of point clouds is a time-consuming process, weakly supervisedapproaches have been introduced to learn from only a small fraction of data.These methods are typically based on learning with contrastive losses whileautomatically deriving per-point pseudo-labels from a sparse set ofuser-annotated labels. In this paper, our key observation is that the selectionof what samples to annotate is as important as how these samples are used fortraining. Thus, we introduce a method for weakly supervised segmentation of 3Dscenes that combines self-training with active learning. The active learningselects points for annotation that likely result in performance improvements tothe trained model, while the self-training makes efficient use of theuser-provided labels for learning the model. We demonstrate that our approachleads to an effective method that provides improvements in scene segmentationover previous works and baselines, while requiring only a small number of userannotations.

Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentation