Research map / Detection and segmentation / Open-set and few-shot detection
Unleashing the Power of Prompt-driven Nucleus Instance Segmentation
Zhongyi Shui, Yunlong Zhang, Kai Yao, Chenglu Zhu, Sunyi Zheng, Jingxiong Li, Honglin Li, YUXUAN SUN, Ruizhe Guo, Lin Yang
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 |
|---|---|---|---|
| fine-tune SAM on nucleus data (one-prompt-one-nucleus) (ablation) | SAM-H with prompter · CPM-17 | PQ: 0.223 -> 0.723 | Improved |
| add auxiliary nuclear region segmentation task to prompter (ablation) | PromptNucSeg-H · CPM-17 | PQ: 0.723 -> 0.727 | Improved |
| add mask-aided prompt filtering at inference (ablation) | PromptNucSeg-H · CPM-17 | PQ: 0.727 -> 0.731 | Improved |
| add one adjacent-nucleus negative prompt in training and testing (ablation) | PromptNucSeg-H · CPM-17 (predicted prompts) | PQ: 0.731 -> 0.733 | Improved |
| add negative prompts only at test time (not in fine-tuning) (ablation) | PromptNucSeg-H · CPM-17 (predicted prompts) | PQ: 0.731 -> 0.730 | No clear effect |
| include negative prompts during fine-tuning (1 negative) (ablation) | PromptNucSeg-H with GT prompts · CPM-17 (oracle GT prompts) | PQ: 0.782 -> 0.790 | Improved |
| increase negative prompts from 1 to 2 with predicted (noisy) prompts (ablation) | PromptNucSeg-H · CPM-17 (predicted prompts) | PQ: 0.733 -> 0.729 | Hurt |
| increase negative prompts from 1 to 2 with ground-truth prompts (ablation) | PromptNucSeg-H · CPM-17 (oracle GT prompts) | PQ: 0.790 -> 0.796 | Improved |
| let prompter rather than segmentor do nucleus classification (ablation) | PromptNucSeg-H · PanNuke | mPQ: 0.506 -> 0.512 | Improved |
| use PromptNucSeg-H instead of best prior methods | nucleus instance segmentation · PanNuke | mPQ: 0.4980 -> 0.5123 | Improved |
Closest papers by meaning
- Mudslide: A Universal Nuclear Instance Segmentation Method (CVPR 2024 · similarity 0.87)
- UniCell: Universal Cell Nucleus Classification via Prompt Learning (AAAI 2024 · similarity 0.86)
- Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation (CVPR 2025 · similarity 0.85)
- Incremental Nuclei Segmentation from Histopathological Images via Future-class Awareness and Compatibility-inspired Distillation (CVPR 2024 · similarity 0.85)
- AoP-SAM: Automation of Prompts for Efficient Segmentation (AAAI 2025 · similarity 0.85)
- One-Prompt to Segment All Medical Images (CVPR 2024 · similarity 0.85)
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.
