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

Various strategies for label-scarce object detection have been explored bythe computer vision research community. These strategies mainly rely onassumptions that are specific to natural images and not directly applicable tothe biological and biomedical vision domains. For example, most semi-supervisedlearning strategies rely on a small set of labeled data as a confident sourceof ground truth. In many biological vision applications, however, the groundtruth is unknown and indirect information might be available in the form ofnoisy estimations or orthogonal evidence. In this work, we frame a crucialproblem in spatial transcriptomics - decoding barcodes from In-Situ-Sequencing(ISS) images - as a semi-supervised object detection (SSOD) problem. Ourproposed framework incorporates additional available sources of informationinto a semi-supervised learning framework in the form of privilegedinformation. The privileged information is incorporated into the teacher'spseudo-labeling in a teacher-student self-training iteration. Although theavailable privileged information could be data domain specific, we haveintroduced a general strategy of pseudo-labeling enhanced by privilegedinformation (PLePI) and exemplified the concept using ISS images, as well onthe COCO benchmark using extra evidence provided by CLIP.

Pseudo-Labeling Enhanced by Privileged Information and Its Application to In Situ Sequencing Images