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

Although there is significant progress in supervised semantic segmentation,it remains challenging to deploy the segmentation models to unseen domains dueto domain biases. Domain adaptation can help in this regard by transferringknowledge from a labeled source domain to an unlabeled target domain. Previousmethods typically attempt to perform the adaptation on global features,however, the local semantic affiliations accounting for each pixel in thefeature space are often ignored, resulting in less discriminability. To solvethis issue, we propose a novel semantic prototype-based contrastive learningframework for fine-grained class alignment. Specifically, the semanticprototypes provide supervisory signals for per-pixel discriminativerepresentation learning and each pixel of source and target domains in thefeature space is required to reflect the content of the corresponding semanticprototype. In this way, our framework is able to explicitly make intra-classpixel representations closer and inter-class pixel representations furtherapart to improve the robustness of the segmentation model as well as alleviatethe domain shift problem. Our method is easy to implement and attains superiorresults compared to state-of-the-art approaches, as is demonstrated with anumber of experiments. The code is publicly available athttps://github.com/BinhuiXie/SPCL.

SPCL: A New Framework for Domain Adaptive Semantic Segmentation via Semantic Prototype-based Contrastive Learning