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 study unsupervised domain adaptation (UDA) for semantic segmentation.Currently, a popular UDA framework lies in self-training which endows the modelwith two-fold abilities: (i) learning reliable semantics from the labeledimages in the source domain, and (ii) adapting to the target domain viagenerating pseudo labels on the unlabeled images. We find that, bydecreasing/increasing the proportion of training samples from the targetdomain, the 'learning ability' is strengthened/weakened while the 'adaptingability' goes in the opposite direction, implying a conflict between these twoabilities, especially for a single model. To alleviate the issue, we propose anovel dual teacher-student (DTS) framework and equip it with a bidirectionallearning strategy. By increasing the proportion of target-domain data, thesecond teacher-student model learns to 'Focus on Your Target' while the firstmodel is not affected. DTS is easily plugged into existing self-trainingapproaches. In a standard UDA scenario (training on synthetic, labeled data andreal, unlabeled data), DTS shows consistent gains over the baselines and setsnew state-of-the-art results of 76.5\% and 75.1\% mIoUs onGTAv$\rightarrow$Cityscapes and SYNTHIA$\rightarrow$Cityscapes, respectively.

Focus on Your Target: A Dual Teacher-Student Framework for Domain-adaptive Semantic Segmentation