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

Semantic image segmentation is a central and challenging task in autonomousdriving, addressed by training deep models. Since this training draws to acurse of human-based image labeling, using synthetic images with automaticallygenerated labels together with unlabeled real-world images is a promisingalternative. This implies to address an unsupervised domain adaptation (UDA)problem. In this paper, we propose a new co-training procedure forsynth-to-real UDA of semantic segmentation models. It consists of aself-training stage, which provides two domain-adapted models, and a modelcollaboration loop for the mutual improvement of these two models. These modelsare then used to provide the final semantic segmentation labels (pseudo-labels)for the real-world images. The overall procedure treats the deep models asblack boxes and drives their collaboration at the level of pseudo-labeledtarget images, i.e., neither modifying loss functions is required, nor explicitfeature alignment. We test our proposal on standard synthetic and real-worlddatasets for on-board semantic segmentation. Our procedure shows improvementsranging from ~13 to ~26 mIoU points over baselines, so establishing newstate-of-the-art results.

Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models