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

Transformers have recently been utilized to perform object detection andtracking in the context of autonomous driving. One unique characteristic ofthese models is that attention weights are computed in each forward pass,giving insights into the model's interior, in particular, which part of theinput data it deemed interesting for the given task. Such an attention matrixwith the input grid is available for each detected (or tracked) object in everytransformer decoder layer. In this work, we investigate the distribution ofthese attention weights: How do they change through the decoder layers andthrough the lifetime of a track? Can they be used to infer additionalinformation about an object, such as a detection uncertainty? Especially inunstructured environments, or environments that were not common duringtraining, a reliable measure of detection uncertainty is crucial to decidewhether the system can still be trusted or not.

Can Transformer Attention Spread Give Insights Into Uncertainty of Detected and Tracked Objects?