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 segmentation is an important sub-task for many applications, butpixel-level ground truth labeling is costly and there is a tendency to overfitthe training data, limiting generalization. Unsupervised domain adaptation canpotentially address these problems, allowing systems trained on labelleddatasets from one or more source domains (including less expensive syntheticdomains) to be adapted to novel target domains. The conventional approach is toautomatically align the representational distributions of source and targetdomains. One limitation of this approach is that it tends to disadvantage lowerprobability classes. We address this problem by introducing a Class-ConditionalDomain Adaptation method (CCDA). It includes a class-conditional multi-scalediscriminator and the class-conditional loss. This novel CCDA method encouragesthe network to shift the domain in a class-conditional manner, and it equalizesloss over classes. We evaluate our CCDA method on two transfer tasks anddemonstrate performance comparable to state-of-the-art methods.

Class-Conditional Domain Adaptation on Semantic Segmentation