Research map / Detection and segmentation / CNN features
Coarse-To-Fine Segmentation With Shape-Tailored Continuum Scale Spaces
Naeemullah Khan, Byung-Woo Hong, Anthony Yezzi, Ganesh Sundaramoorthi
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 single-scale motion residual term with the continuum-scale coarse-to-fine term (ablation) | the motion-segmentation method used by non-ctf · FBMS-59 training set | F-measure: 79.03 -> 81.61 | Improved |
| replace the single-scale motion residual term with the continuum-scale coarse-to-fine term (ablation) | the motion-segmentation method used by non-ctf · FBMS-59 test set | F-measure: 75.82 -> 77.87 | Improved |
| replace the single-scale motion residual term with the continuum-scale coarse-to-fine term (ablation) | the motion-segmentation method used by non-ctf · FBMS-59 training set | recall: 70.74 -> 72.68 | Improved |
| replace the single-scale motion residual term with the continuum-scale coarse-to-fine term (ablation) | the motion-segmentation method used by non-ctf · FBMS-59 test set | precision: 91.47 -> 95.94 | Improved |
Closest papers by meaning
- Coarse-to-Fine Amodal Segmentation with Shape Prior (ICCV 2023 · similarity 0.85)
- Uncertainty-aware Fine-tuning of Segmentation Foundation Models (NeurIPS 2024 · similarity 0.84)
- Learned Shape-Tailored Descriptors for Segmentation (CVPR 2018 · similarity 0.84)
- Combinatorial Energy Learning for Image Segmentation (NeurIPS 2016 · similarity 0.84)
- Improving Image Segmentation with Boundary Patch Refinement (IJCV 2022 · similarity 0.84)
- Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · 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.
