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

Avoiding out-of-distribution (OOD) data is critical for training supervisedmachine learning models in the medical imaging domain. Furthermore, obtaininglabeled medical data is difficult and expensive since it requires expertannotators like doctors, radiologists, etc. Active learning (AL) is awell-known method to mitigate labeling costs by selecting the most diverse oruncertain samples. However, current AL methods do not work well in the medicalimaging domain with OOD data. We propose Diagnose (avoiDing out-of-dIstributiondAta usinG submodular iNfOrmation meaSurEs), a novel active learning frameworkthat can jointly model similarity and dissimilarity, which is crucial in miningin-distribution data and avoiding OOD data at the same time. Particularly, weuse a small number of data points as exemplars that represent a query set ofin-distribution data points and a private set of OOD data points. We illustratethe generalizability of our framework by evaluating it on a wide variety ofreal-world OOD scenarios. Our experiments verify the superiority of Diagnoseover the state-of-the-art AL methods across multiple domains of medicalimaging.

DIAGNOSE: Avoiding Out-of-distribution Data using Submodular Information Measures