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

Semi-supervised learning (SSL) leverages both labeled and unlabeled data fortraining models when the labeled data is limited and the unlabeled data isvast. Frequently, the unlabeled data is more widely available than the labeleddata, hence this data is used to improve the level of generalization of a modelwhen the labeled data is scarce. However, in real-world settings unlabeled datamight depict a different distribution than the labeled dataset distribution.This is known as distribution mismatch. Such problem generally occurs when thesource of unlabeled data is different from the labeled data. For instance, inthe medical imaging domain, when training a COVID-19 detector using chest X-rayimages, different unlabeled datasets sampled from different hospitals might beused. In this work, we propose an automatic thresholding method to filterout-of-distribution data in the unlabeled dataset. We use the Mahalanobisdistance between the labeled and unlabeled datasets using the feature spacebuilt by a pre-trained Image-net Feature Extractor (FE) to score each unlabeledobservation. We test two simple automatic thresholding methods in the contextof training a COVID-19 detector using chest X-ray images. The tested methodsprovide an automatic manner to define what unlabeled data to preserve whentraining a semi-supervised deep learning architecture.

Improving Semi-supervised Deep Learning by using Automatic Thresholding  to Deal with Out of Distribution Data for COVID-19 Detection using Chest  X-ray Images