Research map / Detection and segmentation / Open-set and few-shot detection
Convexity Shape Constraints for Image Segmentation
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 |
|---|---|---|---|
| Add foreground convexity constraints | Two-label Potts model · Nuclei, 2 label Potts | segmentation quality | Helped |
| Add foreground convexity constraints | Two-label Potts model · Fly wing, 2 label Potts | segmentation quality | Helped |
| Add convexity constraints to the yolk label | Three-label Potts model · Fried eggs | energy: 64633 -> 64567 | Helped |
| Add convexity constraints | Three-label Potts model · Synthetic | energy: 3275 -> 3529 | Hurt |
| Add generalized convexity constraints | Three-label Potts model · Apple and orange | segmentation quality | Mixed |
| Add convexity constraints | Correlation clustering · Stone wall | energy: -226 -> -188 | Hurt |
| Add convexity constraints | Correlation clustering · Fly wing | energy: -419 -> -394 | Hurt |
| Use the proposed globally optimizing convexity-constrained method instead of the heuristic | Convex image segmentation · Synthetic and biological examples | solution optimality | Helped |
| Use the proposed method instead of the heuristic | Convex image segmentation · Synthetic and biological examples | runtime | Hurt |
Closest papers by meaning
- D-Convexity: A Unified Differentiable Convex Shape Prior via Quasi-Concavity for Data-driven Image Segmentation (CVPR 2026 · similarity 0.90)
- Implicit Representations for Constrained Image Segmentation (ICML 2024 · similarity 0.84)
- Box Facets and Cut Facets of Lifted Multicut Polytopes (ICML 2024 · similarity 0.84)
- Convex Combination Star Shape Prior for Data-driven Image Semantic Segmentation (CVPR 2025 · similarity 0.84)
- Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · similarity 0.83)
- Higher-Order Ratio Cycles for Fast and Globally Optimal Shape Matching (CVPR 2025 · similarity 0.83)
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.