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/

Zendy Plus

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

Zendy Tools

Zendy Open

Unsupervised domain adaptation(UDA) has been applied to image semanticsegmentation to solve the problem of domain offset. However, in some difficultcategories with poor recognition accuracy, the segmentation effects are stillnot ideal. To this end, in this paper, Intra-subdomain adaptation adversariallearning segmentation method based on Dynamic Pseudo Labels(IDPL) is proposed.The whole process consists of 3 steps: Firstly, the instance-level pseudo labeldynamic generation module is proposed, which fuses the class matchinginformation in global classes and local instances, thus adaptively generatingthe optimal threshold for each class, obtaining high-quality pseudo labels.Secondly, the subdomain classifier module based on instance confidence isconstructed, which can dynamically divide the target domain into easy anddifficult subdomains according to the relative proportion of easy and difficultinstances. Finally, the subdomain adversarial learning module based onself-attention is proposed. It uses multi-head self-attention to confront theeasy and difficult subdomains at the class level with the help of generatedhigh-quality pseudo labels, so as to focus on mining the features of difficultcategories in the high-entropy region of target domain images, which promotesclass-level conditional distribution alignment between the subdomains,improving the segmentation performance of difficult categories. For thedifficult categories, the experimental results show that the performance ofIDPL is significantly improved compared with other latest mainstream methods.

IDPL: Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels