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

Active learning (AL) reduces the amount of labeled data needed to train amachine learning model by intelligently choosing which instances to label.Classic pool-based AL requires all data to be present in a datacenter, whichcan be challenging with the increasing amounts of data needed in deep learning.However, AL on mobile devices and robots, like autonomous cars, can filter thedata from perception sensor streams before reaching the datacenter. Weexploited the temporal properties for such image streams in our work andproposed the novel temporal predicted loss (TPL) method. To evaluate thestream-based setting properly, we introduced the GTA V streets and the A2D2streets dataset and made both publicly available. Our experiments showed thatour approach significantly improves the diversity of the selection while beingan uncertainty-based method. As pool-based approaches are more common inperception applications, we derived a concept for comparing pool-based andstream-based AL, where TPL out-performed state-of-the-art pool- or stream-basedapproaches for different models. TPL demonstrated a gain of 2.5 precept points(pp) less required data while being significantly faster than pool-basedmethods.

Stream-based Active Learning by Exploiting Temporal Properties in Perception with Temporal Predicted Loss