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

Unsupervised domain adaptation (UDA) is an effective approach to handle thelack of annotations in the target domain for the semantic segmentation task. Inthis work, we consider a more practical UDA setting where the target domaincontains sequential frames of the unlabeled videos which are easy to collect inpractice. A recent study suggests self-supervised learning of the object motionfrom unlabeled videos with geometric constraints. We design a motion-guideddomain adaptive semantic segmentation framework (MoDA), that utilizesself-supervised object motion to learn effective representations in the targetdomain. MoDA differs from previous methods that use temporal consistencyregularization for the target domain frames. Instead, MoDA deals separatelywith the domain alignment on the foreground and background categories usingdifferent strategies. Specifically, MoDA contains foreground object discoveryand foreground semantic mining to align the foreground domain gaps by takingthe instance-level guidance from the object motion. Additionally, MoDA includesbackground adversarial training which contains a background category-specificdiscriminator to handle the background domain gaps. Experimental results onmultiple benchmarks highlight the effectiveness of MoDA against existingapproaches in the domain adaptive image segmentation and domain adaptive videosegmentation. Moreover, MoDA is versatile and can be used in conjunction withexisting state-of-the-art approaches to further improve performance.

MoDA: Leveraging Motion Priors from Videos for Advancing Unsupervised Domain Adaptation in Semantic Segmentation