Research map / Detection and segmentation / CNN features
An Error Detection and Correction Framework for Connectomics
Jonathan Zung, Ignacio Tartavull, Kisuk Lee, H. Sebastian Seung
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use the error detector's advice mask instead of the union of all window segments (ablation) | Error-correction framework · Mouse V1 test volume | VI_merge: 0.130 -> 0.088 | Improved |
| Use the error detector's advice mask instead of the union of all window segments (ablation) | Error-correction framework · Mouse V1 test volume | VI_split: 0.057 -> 0.052 | Improved |
| Use the error detector's advice mask instead of the union of all window segments (ablation) | Error-correction framework · Mouse V1 test volume | Rand Recall: 0.956 -> 0.974 | Improved |
| Use the error detector's advice mask instead of the union of all window segments (ablation) | Error-correction framework · Mouse V1 test volume | Rand Precision: 0.979 -> 0.980 | Improved |
| Use error-detector advice to select the candidate mask for correction (ablation) | Error-correction framework · Mouse V1 test volume | Errors: 474 -> 305 | Improved |
| Use error-detector advice to select the candidate mask for correction (ablation) | Error-correction framework · Mouse V1 test volume | Errors fixed: 547 -> 707 | Improved |
| Use error-detector advice to select the candidate mask for correction (ablation) | Error-correction framework · Mouse V1 test volume | Errors introduced: 77 -> 68 | Improved |
| Apply the error corrector only at locations identified by the error detector | Error-correction framework · Connectomics volume processing | Error-correction computation cost: 10× | Improved |
Closest papers by meaning
- Guided Proofreading of Automatic Segmentations for Connectomics (CVPR 2018 · similarity 0.89)
- Large Scale Image Segmentation with Structured Loss Based Deep Learning for Connectome Reconstruction (TPAMI 2018 · similarity 0.85)
- ConnectomeBench: Can LLMs proofread the connectome? (NeurIPS 2025 · similarity 0.83)
- HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging (ICLR 2025 · similarity 0.83)
- Efficient Connectivity-Preserving Instance Segmentation with Supervoxel-Based Loss Function (AAAI 2025 · similarity 0.83)
- Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing (AAAI 2024 · similarity 0.82)
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.
