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

Trust in predictions made by machine learning models is increased if themodel generalizes well on previously unseen samples and when inference isaccompanied by cogent explanations of the reasoning behind predictions. In theimage classification domain, generalization can be assessed through accuracy,sensitivity, and specificity. Explainability can be assessed by how well themodel localizes the object of interest within an image. However, bothgeneralization and explainability through localization are degraded inscenarios with significant overlap between classes. We propose a method basedon binary expert networks that enhances the explainability of imageclassifications through better localization by mitigating the model uncertaintyinduced by class overlap. Our technique performs discriminative localization onimages that contain features with significant class overlap, without explicitlytraining for localization. Our method is particularly promising in real-worldclass overlap scenarios, such as COVID-19 and pneumonia, where expertly labeleddata for localization is not readily available. This can be useful for early,rapid, and trustworthy screening for COVID-19.

Improving Explainability of Image Classification in Scenarios with Class Overlap: Application to COVID-19 and Pneumonia