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

Representation learning in recent years has been addressed withself-supervised learning methods. The input data is augmented into twodistorted views and an encoder learns the representations that are invariant todistortions -- cross-view prediction. Augmentation is one of the key componentsin cross-view self-supervised learning frameworks to learn visualrepresentations. This paper presents ExAgt, a novel method to include expertknowledge for augmenting traffic scenarios, to improve the learntrepresentations without any human annotation. The expert-guided augmentationsare generated in an automated fashion based on the infrastructure, theinteractions between the EGO and the traffic participants and an ideal sensormodel. The ExAgt method is applied in two state-of-the-art cross-viewprediction methods and the representations learnt are tested in downstreamtasks like classification and clustering. Results show that the ExAgt methodimproves representation learning compared to using only standard augmentationsand it provides a better representation space stability. The code is availableat https://github.com/lab176344/ExAgt.

ExAgt: Expert-guided Augmentation for Representation Learning of Traffic Scenarios