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

We present a novel bird's-eye-view (BEV) detector with perspectivesupervision, which converges faster and better suits modern image backbones.Existing state-of-the-art BEV detectors are often tied to certain depthpre-trained backbones like VoVNet, hindering the synergy between booming imagebackbones and BEV detectors. To address this limitation, we prioritize easingthe optimization of BEV detectors by introducing perspective space supervision.To this end, we propose a two-stage BEV detector, where proposals from theperspective head are fed into the bird's-eye-view head for final predictions.To evaluate the effectiveness of our model, we conduct extensive ablationstudies focusing on the form of supervision and the generality of the proposeddetector. The proposed method is verified with a wide spectrum of traditionaland modern image backbones and achieves new SoTA results on the large-scalenuScenes dataset. The code shall be released soon.

BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision