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

## TL;DR

The paper introduces cross-classification clustering (3C), a novel method that efficiently tracks multiple interrelated objects in 3D images, significantly improving scalability and accuracy in connectomics and potentially other domains.

## Contribution

The paper presents 3C, a new clustering-to-classification approach that enhances multi-object tracking efficiency and accuracy, especially in large-scale 3D connectomics datasets.

## Key findings

- Achieves state-of-the-art accuracy in connectomics segmentation.
- Increases scalability by an order of magnitude over existing methods.
- Potential applicability to video and medical image segmentation.

## Abstract

Pixel-accurate tracking of objects is a key element in many computer vision applications, often solved by iterated individual object tracking or instance segmentation followed by object matching. Here we introduce cross-classification clustering (3C), a technique that simultaneously tracks complex, interrelated objects in an image stack. The key idea in cross-classification is to efficiently turn a clustering problem into a classification problem by running a logarithmic number of independent classifications per image, letting the cross-labeling of these classifications uniquely classify each pixel to the object labels. We apply the 3C mechanism to achieve state-of-the-art accuracy in connectomics -- the nanoscale mapping of neural tissue from electron microscopy volumes. Our reconstruction system increases scalability by an order of magnitude over existing single-object tracking methods (such as flood-filling networks). This scalability is important for the deployment of connectomics pipelines, since currently the best performing techniques require computing infrastructures that are beyond the reach of most laboratories. Our algorithm may offer benefits in other domains that require pixel-accurate tracking of multiple objects, such as segmentation of videos and medical imagery.