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

Deep learning models obtain impressive accuracy in road scenes understanding,however they need a large quantity of labeled samples for their training.Additionally, such models do not generalise well to environments where thestatistical properties of data do not perfectly match those of training scenes,and this can be a significant problem for intelligent vehicles. Hence, domainadaptation approaches have been introduced to transfer knowledge acquired on alabel-abundant source domain to a related label-scarce target domain. In thiswork, we design and carefully analyse multiple latent space-shapingregularisation strategies that work together to reduce the domain shift. Morein detail, we devise a feature clustering strategy to increase domainalignment, a feature perpendicularity constraint to space apart featuresbelonging to different semantic classes, including those not present in thecurrent batch, and a feature norm alignment strategy to separate active andinactive channels. In addition, we propose a novel evaluation metric to capturethe relative performance of an adapted model with respect to supervisedtraining. We validate our framework in driving scenarios, considering bothsynthetic-to-real and real-to-real adaptation, outperforming previousfeature-level state-of-the-art methods on multiple road scenes benchmarks.

Road Scenes Segmentation Across Different Domains by Disentangling Latent Representations