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

Noisy labels often occur in vision datasets, especially when they areobtained from crowdsourcing or Web scraping. We propose a new regularizationmethod, which enables learning robust classifiers in presence of noisy data. Toachieve this goal, we propose a new adversarial regularization scheme based onthe Wasserstein distance. Using this distance allows taking into accountspecific relations between classes by leveraging the geometric properties ofthe labels space. Our Wasserstein Adversarial Regularization (WAR) encodes aselective regularization, which promotes smoothness of the classifier betweensome classes, while preserving sufficient complexity of the decision boundarybetween others. We first discuss how and why adversarial regularization can beused in the context of label noise and then show the effectiveness of ourmethod on five datasets corrupted with noisy labels: in both benchmarks andreal datasets, WAR outperforms the state-of-the-art competitors.

Wasserstein Adversarial Regularization (WAR) on label noise