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

Lane detection is one of the core functions in autonomous driving and hasaroused widespread attention recently. The networks to segment lane instances,especially with bad appearance, must be able to explore lane distributionproperties. Most existing methods tend to resort to CNN-based techniques. A fewhave a try on incorporating the recent adorable, the seq2seq Transformer\cite{transformer}. However, their innate drawbacks of weak global informationcollection ability and exorbitant computation overhead prohibit a wide range ofthe further applications. In this work, we propose Atrous Transformer(AtrousFormer) to solve the problem. Its variant local AtrousFormer isinterleaved into feature extractor to enhance extraction. Their collectinginformation first by rows and then by columns in a dedicated manner finallyequips our network with stronger information gleaning ability and bettercomputation efficiency. To further improve the performance, we also propose alocal semantic guided decoder to delineate the identities and shapes of lanesmore accurately, in which the predicted Gaussian map of the starting point ofeach lane serves to guide the process. Extensive results on three challengingbenchmarks (CULane, TuSimple, and BDD100K) show that our network performsfavorably against the state of the arts.

Lane Detection with Versatile AtrousFormer and Local Semantic Guidance