Research map / Detection and segmentation / Open-set and few-shot detection
Sparse Layered Graphs for Multi-Object Segmentation
Niels Jeppesen, Anders N. Christensen, Vedrana A. Dahl, Anders B. Dahl
Check your idea against 137,217 papers
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 |
|---|---|---|---|
| Replace the 4-neighborhood structure with a radially resampled column graph | SLG · Nerve slice | F1: 0.91 -> 0.94 | Improved |
| Replace the 4-neighborhood structure with a radially resampled column graph | SLG · Nerve slice | precision: 0.95 -> 0.93 | Hurt |
| Replace the 4-neighborhood structure with a radially resampled column graph | SLG · Nerve slice | recall: 0.90 -> 0.96 | Improved |
| Use a radially resampled column graph instead of a 4-neighborhood graph | SLG · Nerve slice | nodes (mil.): 2.46 -> 0.58 | Improved |
| Replace the 4-neighborhood structure with a radially resampled column graph | SLG · BBBC038v1 stage1 train | F1: 0.48 -> 0.85 | Improved |
| Replace the 4-neighborhood structure with a radially resampled column graph | SLG · BBBC038v1 stage1 train | recall: 0.40 -> 0.89 | Improved |
| Replace the 4-neighborhood structure with a radially resampled column graph | SLG · BBBC038v1 stage1 train | precision: 0.97 -> 0.85 | Hurt |
| Use a radially resampled column graph rather than a 4-neighborhood graph | SLG · BBBC038v1 stage1 train | nodes (mil.) per image, mean: 2.25 -> 0.71 | Improved |
| Use a radially resampled column graph rather than a 4-neighborhood graph | SLG · BBBC038v1 stage1 train | solve time (s) per image, mean: 2.55 -> 1.02 | Improved |
| Use a radially resampled column graph rather than a 4-neighborhood graph | SLG · BBBC038v1 stage1 train | unlabelled nodes per mask, mean: 3.2 -> 0.48 | Improved |
| Increase interaction margins in a neighborhood-based graph | 4N-SLG · Nerve slice | graph edges | Hurt |
Closest papers by meaning
- Graph-without-cut: An Ideal Graph Learning for Image Segmentation (AAAI 2016 · similarity 0.86)
- Dominant Sets for “Constrained” Image Segmentation (TPAMI 2018 · similarity 0.86)
- GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.86)
- The Mutex Watershed and its Objective: Efficient, Parameter-Free Graph Partitioning (TPAMI 2020 · similarity 0.86)
- Compassionately Conservative Balanced Cuts for Image Segmentation (CVPR 2018 · similarity 0.86)
- SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation (NeurIPS 2025 · similarity 0.84)
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.
