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

This report introduces the 1st place winning solution for the AutonomousDriving Challenge 2023 - Online HD-map Construction. By delving into thevectorization pipeline, we elaborate an effective architecture, termed asMachMap, which formulates the task of HD-map construction as the pointdetection paradigm in the bird-eye-view space with an end-to-end manner.Firstly, we introduce a novel map-compaction scheme into our framework, leadingto reducing the number of vectorized points by 93% without any expressionperformance degradation. Build upon the above process, we then follow thegeneral query-based paradigm and propose a strong baseline with integrating apowerful CNN-based backbone like InternImage, a temporal-based instance decoderand a well-designed point-mask coupling head. Additionally, an extra optionalensemble stage is utilized to refine model predictions for better performance.Our MachMap-tiny with IN-1K initialization achieves a mAP of 79.1 on theArgoverse2 benchmark and the further improved MachMap-huge reaches the best mAPof 83.5, outperforming all the other online HD-map construction approaches onthe final leaderboard with a distinct performance margin (> 9.8 mAP at least).

MachMap: End-to-End Vectorized Solution for Compact HD-Map Construction