AI Paper Atlas

Research map / Detection and segmentation / CNN features

An Error Detection and Correction Framework for Connectomics

Jonathan Zung, Ignacio Tartavull, Kisuk Lee, H. Sebastian Seung

NeurIPS 2017 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the error detector's advice mask instead of the union of all window segments (ablation)Error-correction framework · Mouse V1 test volumeVI_merge: 0.130 -> 0.088Improved
Use the error detector's advice mask instead of the union of all window segments (ablation)Error-correction framework · Mouse V1 test volumeVI_split: 0.057 -> 0.052Improved
Use the error detector's advice mask instead of the union of all window segments (ablation)Error-correction framework · Mouse V1 test volumeRand Recall: 0.956 -> 0.974Improved
Use the error detector's advice mask instead of the union of all window segments (ablation)Error-correction framework · Mouse V1 test volumeRand Precision: 0.979 -> 0.980Improved
Use error-detector advice to select the candidate mask for correction (ablation)Error-correction framework · Mouse V1 test volumeErrors: 474 -> 305Improved
Use error-detector advice to select the candidate mask for correction (ablation)Error-correction framework · Mouse V1 test volumeErrors fixed: 547 -> 707Improved
Use error-detector advice to select the candidate mask for correction (ablation)Error-correction framework · Mouse V1 test volumeErrors introduced: 77 -> 68Improved
Apply the error corrector only at locations identified by the error detectorError-correction framework · Connectomics volume processingError-correction computation cost: 10×Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy