ContactCut: A Partition-Aware Contact Selection Framework for False-Merge Correction in Connectomics
Lists
Only you see this
Abstract
Localized false-merge correction in connectomics requires converting an identified error into an executable native 3D partition. Still, neither intermediate correction predictions nor seeded graph solvers alone determine which native source-sink constraints should define that partition. We formulate this problem as a 3D-native partition-aware contact selection problem: selecting candidate contacts based on the complete partitions they induce. Our solution comprises two components: ContactCut (CC)-Auto, which uses learned single-contact selection, and ContactCut (CC)-Search, which enables bounded paired-contact search, generates compact alternatives, and applies learned panel ranking. On historical two-way false-merge corrections from MICrONS and FlyWire, CC-Auto improves failure-aware 3D partition (FA-3D Part.) mIoU by 5.9 and 3.4 points over the strongest graph-based controls and by 12.5 and 10.0 points over the best learned baselines. A MICrONS-trained ranker transfers to FlyWire with negligible degradation. CC-Search expands oracle reachability and prioritizes near-oracle alternatives. The code is available at https://github.com/bentake/ContactCut.
BibTeX
@misc{ko2026contactcut,
author = {Byunghyun Ko and Won-Ki Jeong and Chaoli Wang},
title = {{ContactCut: A Partition-Aware Contact Selection Framework for False-Merge Correction in Connectomics}},
year = {2026},
eprint = {2611.01457},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.01457},
}Loading related content...