Research map / Detection and segmentation / Open-set and few-shot detection
Focus on Background: Exploring SAM's Potential in Few-shot Medical Image Segmentation with Background-centric Prompting
Yuntian Bo, Yazhou Zhu, Piotr Koniusz, Haofeng Zhang
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 BCM context modeling (ablation) | FoB + SAM · Abd-CT Setting I | Dice (%): 81.01 -> 83.49 (BPPC only vs +BCM) | Improved |
| add SPR structure-guided refinement (ablation) | FoB + SAM · Abd-CT Setting I | Dice (%): 85.12 -> 86.21 | Improved |
| add region-aware contrastive loss Lrac (ablation) | FoB + SAM · Abd-CT Setting I | Dice (%): 83.93 -> 86.21 | Improved |
| add foreground loss Lfore (ablation) | FoB + SAM · Abd-CT Setting I | Dice (%): 70.45 -> 86.21 | Improved |
| add heatmap loss Lheat alongside coordinate regression (ablation) | FoB + SAM · Abd-CT Setting I | Dice (%): 35.26 -> 86.21 | Improved |
| add background prompts to SAM (ablation) | FoB + SAM · Abd-CT | Dice (%) | Improved |
| use medical SAM (SAM-Med2D) instead of SAM (ablation) | FoB · Skin-DS Setting I | Dice (%): 76.62 -> 84.80; Abd-CT 86.21 -> 80.70 | Mixed |
| use FoB prompts with SAM instead of AM-SAM | FoB + SAM · Abd-CT Setting I | Dice (%): 86.19 -> 86.21 | No clear effect |
| use FoB+SAM instead of FAMNet in cross-domain | FoB + SAM · CT->MRI | Dice (%): 65.79 -> 73.30 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PGRNet — PGR-Net: Prior-Guided ROI Reasoning Network for Brain Tumor MRI Segmentation (CVPR 2026) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- One-Prompt to Segment All Medical Images (CVPR 2024 · similarity 0.88)
- Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation (CVPR 2025 · similarity 0.87)
- CAT: Coordinating Anatomical-Textual Prompts for Multi-Organ and Tumor Segmentation (NeurIPS 2024 · similarity 0.87)
- Rethinking Interactive Image Segmentation with Low Latency High Quality and Diverse Prompts (CVPR 2024 · similarity 0.86)
- AoP-SAM: Automation of Prompts for Efficient Segmentation (AAAI 2025 · similarity 0.86)
- SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation (AAAI 2025 · 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.
