Research map / Detection and segmentation / Open-set and few-shot detection
Learning and Aligning Click-Aware Shape Prior for Interactive Amodal Instance Segmentation
Junjie Chen, Junwei Lin, Ren Hong, Shengjie Liu, Yuming Fang, Feng Qian, Yifan Zuo
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 standard shape prior retrieval to a clicks-only model (ablation) | ClickPriorNet · KINS | mIoU occ (3 clicks): 54.02 -> 58.17 | Improved |
| replace standard shape prior with click-aware shape prior (triplet loss) (ablation) | ClickPriorNet · KINS | mIoU occ (3 clicks): 58.17 -> 67.86 | Improved |
| add deformable-attention prior alignment (ablation) | ClickPriorNet · KINS | mIoU occ (3 clicks): 67.86 -> 73.16 | Improved |
| add click-aware shape prior to a clicks-only model (NoC85) (ablation) | ClickPriorNet · KINS | NoC85 occ: 2.85 -> 2.40 | Improved |
| use ClickPriorNet instead of MFP+C2F | interactive amodal segmentation · KINS | NoC90 occ: 4.65 -> 4.31 | Improved |
| combine MFP with C2F-Seg shape prior | MFP · KINS | NoC90 occ: 4.76 -> 4.65 | Improved |
| use ClickPriorNet instead of MFP+C2F with 1 click | interactive amodal segmentation · KINS, 1 click | mIoU occ: 55.11 -> 56.32 | Improved |
| use ClickPriorNet instead of MFP+C2F with 5 clicks | interactive amodal segmentation · KINS, 5 clicks | mIoU occ: 73.35 -> 77.72 | Improved |
| use ClickPriorNet instead of MFP+C2F with 3 clicks | interactive amodal segmentation · COCOA cls, 3 clicks | mIoU occ: 41.94 -> 49.39 | Improved |
| use ClickPriorNet instead of MFP+C2F with 3 clicks | interactive amodal segmentation · KINS, 3 clicks | mIoU occ: MFP+C2F 3 clicks 67.70 vs Ours 73.16 | Mixed |
| use too small top-N (N = 6) in triplet loss (ablation) | ClickPriorNet · KINS | NoC85 occ and mIoU occ | Hurt |
| use too few retrieved priors (K = 4), or K above 10 (ablation) | ClickPriorNet · KINS | NoC85 occ and mIoU occ | Mixed |
Closest papers by meaning
- BLADE: Box-Level Supervised Amodal Segmentation through Directed Expansion (AAAI 2024 · similarity 0.88)
- Using Diffusion Priors for Video Amodal Segmentation (CVPR 2025 · similarity 0.88)
- Order-aware Interactive Segmentation (ICLR 2025 · similarity 0.87)
- Segment Anything, Even Occluded (CVPR 2025 · similarity 0.86)
- Towards Efficient Foundation Model for Zero-shot Amodal Segmentation (CVPR 2025 · similarity 0.86)
- Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes (ICML 2025 · 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.
