Research map / Graph learning / Graph algorithms and clustering
Active Learning for Delineation of Curvilinear Structures
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 probability propagation over neighboring graph paths to select uncertain samples | Active learning for curvilinear delineation · Synthetic dataset | classification performance: 90 examples | Helped |
| Add density-based batch selection to probability propagation sampling | PPS · Synthetic dataset | classification performance | Helped |
| Use probability propagation and density-based selection | Curvilinear delineation active learning · Roads | annotation effort to reach Full performance: 75% reduction | Helped |
| Use probability propagation and density-based selection | Curvilinear delineation active learning · Roads | DIADEM score | Helped |
| Use probability propagation and density-based selection | Curvilinear delineation active learning · Blood vessels | classification performance | Helped |
| Use probability propagation and density-based selection | Curvilinear delineation active learning · Axons | annotation effort: 65% reduction | Helped |
| Use probability propagation and density-based selection | Curvilinear delineation active learning · Brightfield neurons | VOC score | Helped |
| Add density-based query selection | PPS · Roads | classification performance early in learning | Helped |
| Query pairs of consecutive paths instead of singletons or triplets (ablation) | DPS · Roads | classification performance | Helped |
| Use PPS or DPS instead of conventional sampling | Active learning for curvilinear delineation · Roads | variance: 0.00055 -> 0.00036; 0.00055 -> 0.00031 | Helped |
| Use DPS instead of QBC | Active learning for curvilinear delineation · Axons | variance: 0.00047 -> 0.00043 | Helped |
Closest papers by meaning
- Beyond the Pixel-Wise Loss for Topology-Aware Delineation (CVPR 2018 · similarity 0.85)
- DeepBranchTracer: A Generally-Applicable Approach to Curvilinear Structure Reconstruction Using Multi-Feature Learning (AAAI 2024 · similarity 0.83)
- Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation (NeurIPS 2024 · similarity 0.82)
- GraphMorph: Tubular Structure Extraction by Morphing Predicted Graphs (NeurIPS 2024 · similarity 0.82)
- Boundary Matters: A Bi-Level Active Finetuning Method (NeurIPS 2024 · similarity 0.82)
- Constraint-Free Structure Learning with Smooth Acyclic Orientations (ICLR 2024 · similarity 0.81)
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.