Research map / Detection and segmentation / CNN features
Interactive Segmentation with Elaborate Focus Prior
Kangpeng Hu, Yinghui Sun, Tao Wang, Weihao Zhang, Quansen Sun
Read the paperCheck 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 |
|---|---|---|---|
| add focus view predictor (FVP) (ablation) | FCFI baseline (ViT-B) · SBD | NoC@85 and NoC@90: 0.17 for NoC%85 and 0.28 for NoC%90; 3.49 -> 3.32; 5.83 -> 5.55 | Improved |
| add focus view predictor (FVP) (ablation) | FCFI baseline (ViT-B) · Berkeley | NoC@85 and NoC@90: 0.09 for NoC%85 and 0.08 for NoC%90; 1.49 -> 1.40; 1.97 -> 1.91 | Improved |
| add triple-affinity correction (TAC) (ablation) | FCFI baseline (ViT-B) · SBD | NoC@85 and NoC@90: 0.1 NoC%85 and 0.12 NoC%90; 3.49 -> 3.39; 5.83 -> 5.71 | Improved |
| add clicked-with-focus integration (CFI: FCL and FA) (ablation) | EFPNet · SBD | NoC@85 and NoC@90: 0.12 NoC%85 and 0.12 NoC%90 | Improved |
| add all components (FVP, TAC, FCL, FA) (ablation) | FCFI baseline (ViT-B) · SBD | NoC@90: 5.83 -> 5.27 | Improved |
| use learnable TAC affinity weights instead of average mixture 0.5/0.5/0.5 (ablation) | TAC · SBD | NoC@90: 5.31 -> 5.27 | Improved |
| use learnable weights instead of pixel-only affinity (lambda_P=1) (ablation) | TAC · Berkeley | NoC@90: 2.08 -> 1.87; up to 0.29 NoC%90 gain | Improved |
| use mask-only affinity instead of pixel-only affinity (ablation) | TAC · SBD | NoC@90: 5.69 -> 5.44 | Improved |
| use EFPNet instead of FCFI with same backbone and data | FCFI · GrabCut/Berkeley/DAVIS/SBD | NoC: around 0.2 to 0.4 NoC | Improved |
| use EFPNet instead of FCFI (ResNet-101) | FCFI · Berkeley | FIoU: 0.117 -> 0.609 | Improved |
| use EFPNet instead of FCFI (ResNet-101) | FCFI · ResNet-101 efficiency | seconds per click: 0.023 -> 0.029 | Hurt |
| use EFPNet instead of FocusCut on GrabCut | FocusCut · GrabCut | NoC@85: 1.46 -> 1.54 | Hurt |
Closest papers by meaning
- NTClick: Achieving Precise Interactive Segmentation With Noise-tolerant Clicks (CVPR 2025 · similarity 0.88)
- Order-aware Interactive Segmentation (ICLR 2025 · similarity 0.88)
- FocSAM: Delving Deeply into Focused Objects in Segmenting Anything (CVPR 2024 · similarity 0.87)
- CFR-ICL: Cascade-Forward Refinement with Iterative Click Loss for Interactive Image Segmentation (AAAI 2024 · similarity 0.87)
- TETRIS: Towards Exploring the Robustness of Interactive Segmentation (AAAI 2024 · similarity 0.86)
- RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation (NeurIPS 2024 · similarity 0.86)
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.
