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

Deep Neural Networks (DNNs) suffer from domain shift when the test datasetfollows a distribution different from the training dataset. Domaingeneralization aims to tackle this issue by learning a model that cangeneralize to unseen domains. In this paper, we propose a new approach thataims to explicitly remove domain-specific features for domain generalization.Following this approach, we propose a novel framework called Learning andRemoving Domain-specific features for Generalization (LRDG) that learns adomain-invariant model by tactically removing domain-specific features from theinput images. Specifically, we design a classifier to effectively learn thedomain-specific features for each source domain, respectively. We then developan encoder-decoder network to map each input image into a new image space wherethe learned domain-specific features are removed. With the images output by theencoder-decoder network, another classifier is designed to learn thedomain-invariant features to conduct image classification. Extensiveexperiments demonstrate that our framework achieves superior performancecompared with state-of-the-art methods.

Domain Generalization by Learning and Removing Domain-specific Features