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

Pixel-accurate tracking of objects is a key element in many computer visionapplications, often solved by iterated individual object tracking or instancesegmentation followed by object matching. Here we introducecross-classification clustering (3C), a technique that simultaneously trackscomplex, interrelated objects in an image stack. The key idea incross-classification is to efficiently turn a clustering problem into aclassification problem by running a logarithmic number of independentclassifications per image, letting the cross-labeling of these classificationsuniquely classify each pixel to the object labels. We apply the 3C mechanism toachieve state-of-the-art accuracy in connectomics -- the nanoscale mapping ofneural tissue from electron microscopy volumes. Our reconstruction systemincreases scalability by an order of magnitude over existing single-objecttracking methods (such as flood-filling networks). This scalability isimportant for the deployment of connectomics pipelines, since currently thebest performing techniques require computing infrastructures that are beyondthe reach of most laboratories. Our algorithm may offer benefits in otherdomains that require pixel-accurate tracking of multiple objects, such assegmentation of videos and medical imagery.

Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics